CN110083733A - Picture examination method, apparatus, equipment and computer readable storage medium - Google Patents
Picture examination method, apparatus, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN110083733A CN110083733A CN201910200477.7A CN201910200477A CN110083733A CN 110083733 A CN110083733 A CN 110083733A CN 201910200477 A CN201910200477 A CN 201910200477A CN 110083733 A CN110083733 A CN 110083733A
- Authority
- CN
- China
- Prior art keywords
- source
- picture
- houses
- houses picture
- examination
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000012795 verification Methods 0.000 claims abstract description 82
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 23
- 238000012384 transportation and delivery Methods 0.000 claims abstract description 19
- 238000012552 review Methods 0.000 claims abstract description 13
- 238000012550 audit Methods 0.000 claims description 55
- 230000006835 compression Effects 0.000 claims description 10
- 238000007906 compression Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 19
- 230000006870 function Effects 0.000 description 9
- 238000012545 processing Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 239000000284 extract Substances 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000012512 characterization method Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 239000002872 contrast media Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000002187 spin decoupling employing ultra-broadband-inversion sequences generated via simulated annealing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Library & Information Science (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The present invention provides a kind of picture examination method based on image matching algorithm, comprising: obtains the first source of houses picture that user uploads when source of houses delivery system issues the source of houses;The second source of houses picture prestored in first source of houses picture and presetting database is subjected to Characteristic Contrast, the preset condition for meeting prompt manual examination and verification is determined whether according to comparing result;If satisfied, then obtaining target second source of houses picture for meeting the preset condition, and the prompt information that prompt auditor carries out manual examination and verification is generated based on target second source of houses picture;The auditing result information that auditor submits is obtained, the final review result of first source of houses picture is determined based on the auditing result information.The present invention also provides a kind of picture examination device, equipment and computer readable storage mediums.The efficiency that source of houses picture is usurped in identification can be improved in the present invention.
Description
Technical field
The present invention relates to picture process field more particularly to a kind of picture examination method, apparatus, equipment and computer-readable
Storage medium.
Background technique
Entity all needs to upload source of houses picture when issuing the source of houses, and source of houses picture most can intuitively attract clients
The case where consulting source of houses, often will appear and usurp other people source of houses photos, and more suites use the same photo, more room users are on website
See satisfied source of houses picture, waits and have been found that picture is faked when seeing room, generally can be poorer than the room environment shown on picture, because
And it will cause many unnecessary troubles.And whether website side will not be generally that stolen picture is audited to picture, because
It is a huge engineering for audit source of houses picture, solves to be substantially impossible mission by manpower, so far,
There are no occur that the means for usurping source of houses picture can be efficiently identified.
Summary of the invention
The main purpose of the present invention is to provide a kind of picture examination method, apparatus, equipment and computer-readable storage mediums
Matter, it is intended to improve the efficiency that source of houses picture is usurped in identification.
To achieve the above object, the present invention provides a kind of picture examination method, and the picture examination method includes following step
It is rapid:
Obtain the first source of houses picture that user uploads when source of houses delivery system issues the source of houses;
The second source of houses picture prestored in first source of houses picture and presetting database is subjected to Characteristic Contrast, according to
Comparing result determines whether the preset condition for meeting prompt manual examination and verification;
If satisfied, then obtaining target second source of houses picture for meeting the preset condition, and it is based on second room of target
Source picture generates the prompt information that prompt auditor carries out manual examination and verification;
The auditing result information that auditor submits is obtained, first source of houses picture is determined based on the auditing result information
Final review result.
Optionally, second source of houses picture prestored by first source of houses picture and presetting database carries out special
Sign comparison determines whether that the step of meeting the preset condition of prompt manual examination and verification includes: according to comparing result
Determine that algorithm determines the condition code of first source of houses picture and the spy of the second source of houses picture based on default condition code
Levy code, wherein described document information includes at least informative abstract MD5 code or Color Distribution Features code;
The condition code of first source of houses picture and the condition code of the second source of houses picture are compared, determine described first
The condition code matching degree of source of houses picture and the second source of houses picture;
Described document information matching degree is compared with default condition code matching degree, whether judges described document information matching degree
More than or equal to default condition code matching degree;
If described document information matching degree is greater than or equal to the default condition code matching degree, determine that meeting prompt manually examines
The preset condition of core;
It is described to obtain target second source of houses picture for meeting the preset condition, and it is based on second source of houses of the target picture
Generating the step of prompt auditor carries out the prompt information of manual examination and verification includes:
Target second source of houses picture for meeting the preset condition is obtained, and according to second source of houses of the target picture, institute
It states the first source of houses picture and the matching degree generates the prompt information that prompt auditor carries out manual examination and verification.
Optionally, described to determine that algorithm determines the condition code and the second room of first source of houses picture based on default condition code
The step of condition code of source picture, replaces are as follows:
Determine the condition code for calculating fixed first source of houses picture based on the default condition code, and from the presetting database
The middle pre-stored characteristics code for obtaining the second source of houses picture, using the condition code as the second source of houses picture.
Optionally, the base determines the final review result of first source of houses picture based on the auditing result information
Include: after step
When auditing result is that audit passes through, first source of houses picture and its condition code are stored in the preset data
In library, and the first source of houses picture being stored in the presetting database is associated with its condition code.
Optionally, the step of the final review result that first source of houses picture is determined based on the auditing result information
Include: after rapid
When auditing result is to audit obstructed out-of-date, audit is generated not by prompt information based on first source of houses picture,
And the audit is not sent to the user terminal for uploading the user of first source of houses picture by prompt information.
Optionally, second source of houses picture prestored by first source of houses picture and presetting database carries out special
Sign comparison determines whether that the step of meeting the preset condition of prompt manual examination and verification includes: according to comparing result
The characteristic point information of first source of houses picture is extracted based on default feature point extraction algorithm;
The pre-stored characteristics point information of the characteristic point information of first source of houses picture and second source of houses picture is carried out
Comparison, matching characteristic point quantity and first source of houses picture based on first source of houses picture and second source of houses picture
The ratio of characteristic point sum determines the Feature Points Matching degree of first source of houses picture Yu second source of houses picture;
The Feature Points Matching degree and default Feature Points Matching degree are compared, determine the Feature Points Matching degree and institute
State whether default Feature Points Matching degree is greater than or equal to the default Feature Points Matching degree;
If so, determining the preset condition for meeting prompt manual examination and verification.
Optionally, described document information is Color Distribution Features code, first source of houses picture or second source of houses picture
The determination method of Color Distribution Features code include:
By first source of houses picture or second source of houses picture compression to presetted pixel size, compressed room is obtained
Source picture;
Determine the grey parameter of each pixel of compressed source of houses picture and the average value of grey parameter;
By the size comparison result of the grey parameter of each pixel and the average value determine first source of houses picture or
The Color Distribution Features code of second source of houses picture.
In addition, to achieve the above object, the present invention also provides a kind of picture examination device, the picture examination device packet
It includes:
First obtains module, the first source of houses picture uploaded for obtaining user when source of houses delivery system issues the source of houses;
The second source of houses picture prestored in first source of houses picture and presetting database is carried out feature by contrast module
Comparison determines whether the preset condition for meeting prompt manual examination and verification according to comparing result;
First generation module, for meeting target second source of houses picture of the preset condition, and base if satisfied, then obtaining
The prompt information that prompt auditor carries out manual examination and verification is generated in target second source of houses picture;
Second obtains module, true based on the auditing result information for obtaining the auditing result information of auditor's submission
The final review result of fixed first source of houses picture.
In addition, to achieve the above object, the present invention also provides a kind of picture examination equipment, the picture examination equipment includes
Processor, memory and it is stored in the picture examination program that can be executed on the memory and by the processor, wherein institute
When stating picture examination program and being executed by the processor, realize such as the step of above-mentioned picture examination method.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage medium
Picture examination program is stored on storage medium, wherein realizing when the picture examination program is executed by processor as above-mentioned
The step of picture examination method.
The present invention provides a kind of picture examination method, apparatus, equipment and computer readable storage medium, and the picture is examined
Kernel method includes: the first source of houses picture for obtaining user and uploading when source of houses delivery system issues the source of houses;By first source of houses
The second source of houses picture prestored in picture and presetting database carries out Characteristic Contrast, determines whether that satisfaction mentions according to comparing result
Show the preset condition of manual examination and verification;If satisfied, then obtaining target second source of houses picture for meeting the preset condition, and it is based on institute
It states target second source of houses picture and generates the prompt information that prompt auditor carries out manual examination and verification;Obtain the audit knot that auditor submits
Fruit information determines the final review result of first source of houses picture based on the auditing result information.By the above-mentioned means,
When the source of houses picture uploaded when obtaining user's publication source of houses, first automatically the source of houses picture currently uploaded is uploaded with history pre-
It deposits source of houses picture and carries out Characteristic Contrast, after Characteristic Contrast result meets specific preset condition, just prompt carries out manual examination and verification, real
The audit mode of existing man-computer cooperation, the picture that auditor need to only meet particular preset condition to automated characterization comparing result are examined
Core, and when manual examination and verification, there are the target second picture of robber's figure suspicion it has been determined that auditor has room without carrying out magnanimity
The comparison one by one of source picture, thus greatly reduces manpower, efficiently identifies the case where usurping source of houses picture.
Detailed description of the invention
Fig. 1 is the hardware structural diagram of picture examination equipment involved in the embodiment of the present invention;
Fig. 2 is the flow diagram of picture examination method first embodiment of the present invention;
Fig. 3 is the flow diagram of picture examination method second embodiment of the present invention;
Fig. 4 is the flow diagram of picture examination method 3rd embodiment of the present invention;
Fig. 5 is the flow diagram of picture examination method fourth embodiment of the present invention;
Fig. 6 is the flow diagram of the 5th embodiment of picture examination method of the present invention;
Fig. 7 is the flow diagram of picture examination method sixth embodiment of the present invention;
Fig. 8 is the flow diagram of the 7th embodiment of picture examination method of the present invention;
Fig. 9 is the functional block diagram of picture examination device of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The present embodiments relate to picture examination method be mainly used in picture examination equipment, which can
To be that personal computer (personal computer, PC), portable computer, mobile terminal etc. are having data processing function
Equipment.
Referring to Fig.1, Fig. 1 is the hardware structural diagram of picture examination equipment involved in the embodiment of the present invention.This
In inventive embodiments, picture examination equipment may include (such as the central processing unit Central Processing of processor 1001
Unit, CPU), communication bus 1002, user interface 1003, network interface 1004, memory 1005.Wherein, communication bus 1002
For realizing the connection communication between these components;User interface 1003 may include display screen (Display), input unit ratio
Such as keyboard (Keyboard);Network interface 1004 optionally may include standard wireline interface and wireless interface (such as Wireless Fidelity
WIreless-FIdelity, WI-FI interface);Memory 1005 can be high-speed random access memory (random access
Memory, RAM), it is also possible to stable memory (non-volatile memory), such as magnetic disk storage, memory
1005 optionally can also be the storage device independently of aforementioned processor 1001.It will be understood by those skilled in the art that in Fig. 1
The hardware configuration that shows does not constitute a limitation of the invention simultaneously, may include than illustrating more or fewer components, or combination
Certain components or different component layouts.
With continued reference to Fig. 1, the memory 1005 in Fig. 1 as a kind of computer readable storage medium may include operation system
System, network communication module and picture examination program.In Fig. 1, network communication module can be used for connecting server, with server
Carry out data communication;And processor 1001 can call the picture examination program stored in memory 1005, and execute the present invention
The picture examination method that embodiment provides.
The embodiment of the invention provides a kind of picture examination methods.
It is the flow diagram of picture examination method first embodiment of the present invention referring to Fig. 2, Fig. 2.
Entity all needs to upload source of houses picture when issuing the source of houses, and source of houses picture most can intuitively attract clients
The case where consulting source of houses, often will appear and usurp other people source of houses photos, and more suites use the same photo, more room users are on website
See satisfied source of houses picture, waits and have been found that picture is faked when seeing room, generally can be poorer than the room environment shown on picture, because
And it will cause many unnecessary troubles.And whether website side will not be generally that stolen picture is audited to picture, because
It is a huge engineering for audit source of houses picture, solves to be substantially impossible mission by manpower, so far,
There are no occur that the means for usurping source of houses picture can be efficiently identified.
In the present embodiment, the picture examination method the following steps are included:
Step S10 obtains the first source of houses picture that user uploads when source of houses delivery system issues the source of houses;
Present invention is mainly applied to image processing technologies, such as the processing technology field of house property picture.Of the invention
Picture detection method can be by source of houses delivery system or other server external with source of houses delivery system execution.Source of houses publication
The system that system can be various source of houses issuing web sites, such as rent a house website or house prosperity transaction website etc. first obtain landlord, intermediary
Or the first source of houses picture that the users such as House Resource Management people upload when source of houses delivery system issues the source of houses, the first room of the invention
Source picture refers to obtaining in real time when user issues the source of houses, carries out audit and determining whether there is to usurp suspicion detection
First source of houses picture, that is, the audit object of technical solution of the present invention.The first source of houses picture that user uploads when issuing the source of houses
It may include multiple source of houses pictures of the different scenes types such as main Room picture, bedroom picture or kitchen picture, user uploaded
Every first source of houses picture, picture examination method of the invention is executed since step S10.
The second source of houses picture prestored in first source of houses picture and presetting database is carried out feature by step S20
Comparison determines whether the preset condition for meeting prompt manual examination and verification according to comparing result;
Presetting database refers to the source of houses for storing existing source of houses picture, including being uploaded to source of houses delivery system
Picture or the disclosed source of houses picture obtained from source of houses picture website disclosed in other.Second source of houses picture refers to above-mentioned deposit
Storage source of houses picture in the preset database, namely it is uploaded to the source of houses picture of source of houses delivery system or source of houses disclosed in other
The disclosed source of houses picture obtained in picture website, presetting database may include the source of houses picture of multiple and different scene types.
Some specific user may upload multiple and different figures of the multiple and different scene types of the source of houses when issuing an information of real estate
Piece, every first source of houses picture uploaded for user are carried out contrast operation: will be in the first source of houses picture and presetting database
The second all source of houses pictures carry out Characteristic Contrast one by one, obtain first source of houses picture respectively with each second source of houses picture
Characteristic Contrast result.After executing above-mentioned contrast operation to all first source of houses pictures, obtain all first source of houses pictures with it is each
The corresponding comparing result of second source of houses picture.It include obtaining each the respectively by the first source of houses picture and the second source of houses picture
The characteristic information of one source of houses picture and each second source of houses picture, and by the characteristic information of the first source of houses picture and the second source of houses figure
The characteristic information of piece compares, and determines the matching degree of two source of houses picture feature information, using determining matching degree as two
The comparing result of picture.Prompt manual examination and verification preset condition refer to it is pre-set, be based on comparing result to determine whether
The condition for prompting to carry out manual examination and verification is needed, when meeting the preset condition of prompt manual examination and verification, passes through preset prompt
Information prompts the related auditor to carry out manual examination and verification to picture, and the setting principle of preset condition is, if the first source of houses picture with
When second source of houses picture reaches specific similarity degree, then prompt carries out people to corresponding first source of houses picture and the second source of houses picture
Work audit.Specifically, it includes but is not limited to three kinds following for carrying out Characteristic Contrast: 1) information that can calculate separately each picture is plucked
MD5 code is wanted, for each first source of houses picture, respectively by all second source of houses pictures in the MD5 code of picture and presetting database
MD5 code compared one by one, determine every two comparison picture MD5 code it is whether consistent, if two pictures MD5 code unanimously,
Then determine that corresponding two pictures are identical picture, the matching degree of picture is 100%;If the MD5 code of two pictures is inconsistent,
Determine that corresponding picture is different pictures, the matching degree of picture non-100%.The preset condition of corresponding prompt manual examination and verification is picture
MD5 code matching degree is 100%, that is, if the MD5 code matching degree of two pictures is 100%, determines that comparing result meets prompter
The preset condition of work audit determines that comparing result is unsatisfactory for prompter if the MD5 code matching degree of two pictures is not 100%
The preset condition of work audit.2) compression processing is carried out to each picture respectively, by picture compression to presetted pixel size, such as
8x8, totally 64 pixels, determine the corresponding grey parameter of each pixel, calculate the average gray parameter of all 64 pixels, then will
The grey parameter of each pixel is compared with average gray parameter, is denoted as 1 more than or equal to average gray parameter, is less than flat
Equal grey parameter is denoted as 0, to obtain corresponding 64 integers of 64 pixels, loses 64 integers based on specific preset order
It is arranged, obtains the sub-sequence fingerprint of each picture, i.e. picture color distribution characteristics code.It, will for each first source of houses picture
The Color Distribution Features code of first source of houses picture and the Color Distribution Features code of second source of houses pictures all in presetting database are each
Numerical value in a corresponding numerical digit is compared one by one, determines that corresponding two picture color distribution characteristics codes correspond to numerical value phase in numerical digit
The ratio of same digit and Color Distribution Features code total bit, using the ratio as the color characteristic code matching degree of two pictures.
A color characteristic code matching degree threshold value, such as 90% can be preset, the preset condition of corresponding prompt manual examination and verification can be set
Be set to: the color characteristic code matching degree of two pictures is greater than or equal to pre-set color condition code matching degree threshold value, that is, schemes when two
When the color characteristic code matching degree of piece is greater than or equal to pre-set color condition code matching degree threshold value, the comparison of the two pictures is determined
As a result meet the preset condition of prompt manual examination and verification;If the color characteristic code matching degree of two pictures is less than pre-set color condition code
Matching degree threshold value then determines that the comparing result of the two pictures is unsatisfactory for the preset condition of prompt manual examination and verification.3) it is based on feature
Point extraction algorithm, such as SFIT algorithm, extract the characteristic point of each source of houses picture, for each first source of houses picture, by the source of houses
The characteristic point of picture and the characteristic point of the second all source of houses pictures compare respectively, determine the source of houses picture with respectively and respectively
The ratio of the characteristic point quantity of a second source of houses picture match and the source of houses picture feature point sum, i.e. matching characteristic point ratio,
The matching degree that matching characteristic point ratio is compared between picture as two.It can preset with Feature Points Matching degree threshold value,
Such as 85%, the preset condition of corresponding prompt manual examination and verification can be set as: the Feature Points Matching degree of two pictures is greater than or waits
In default Feature Points Matching degree threshold value, that is, when the Feature Points Matching degree of two pictures is greater than or equal to default Feature Points Matching degree
When threshold value, determine that the comparing result of two pictures meets the preset condition of prompt manual examination and verification;If the characteristic point of two pictures
It is less than default Feature Points Matching degree threshold value with degree, then determines that the comparing result of the two pictures is unsatisfactory for the pre- of prompt manual examination and verification
If condition.
Step S30 if satisfied, then obtaining target second source of houses picture for meeting the preset condition, and is based on the mesh
It marks the second source of houses picture and generates the prompt information that prompt auditor carries out manual examination and verification;
Based on step S20, during carrying out picture examination to the first source of houses picture, however, it is determined that wherein first room
The comparing result of one or more specific second source of houses picture meets prompt manual examination and verification in source picture and presetting database
When preset condition, acquisition meets preset condition corresponding one or more the first source of houses picture, i.e. second source of houses of target picture, base
The prompt information that prompt auditor carries out manual examination and verification is generated in target second source of houses picture, for prompting auditor to be based on prompt
Information carries out manual examination and verification to all pictures of the source of houses or specific first source of houses picture corresponding with target second source of houses picture.
Specifically, prompt information is the form that picture enclosure adds text prompt information, and text prompt information, which can be, " retrieves similar diagram
Piece, come in, and row audit determines ", picture enclosure is the attachment of second source of houses of target picture.It in the present embodiment, can be by generation
Prompt information is stored in preset memory locations, logs in the account number login source of houses by pre-assigned auditor when receiving auditor
When delivery system, account number is logged in based on auditor and sends the terminal device for carrying out the prompt information of manual examination and verification to auditor.When
So, can also the equipment identification information based on auditor's terminal device the prompt information of generation is directly sent to end of auditor
End equipment.
Further, in the present embodiment, in the comparison for determining specific first source of houses picture Yu specific second source of houses picture
When as a result meeting the preset condition of prompt manual examination and verification, then specific second source of houses picture is target source of houses picture, and being based on should
Comparing result (the i.e. matching of picture of specific first source of houses picture and specific second source of houses picture and the two pictures
Degree), generate the prompt information that prompt auditor carries out manual examination and verification.
Step S40 obtains the auditing result information that auditor submits, determines described first based on the auditing result information
The final review result of source of houses picture.
It in the present embodiment, can the audits knot such as preset in source of houses delivery system " audit passes through " and " audit does not pass through "
The submission function button of fruit information.After auditor checks prompt information, corresponding submission is passed through based on actual auditing result
Function button submits auditing result information.Specifically, if auditor is after audit is audited based on manual examination and verification prompt information,
If audit conclusion is to pass through, the auditing result that audit can be submitted to pass through by the function button of preset " audit passes through " is believed
Breath;If auditing conclusion is that audit is obstructed out-of-date, audit can be submitted not by the function button of preset " audit does not pass through "
By result information.Source of houses delivery system obtains the former audit submitted of audit and passes through or audit unacceptable auditing result information
When, using the auditing result in auditing result information as the final review of first source of houses picture as a result, being first source of houses figure
Piece whether be robber's figure picture auditing result.
In the present embodiment, the first source of houses picture that user uploads when source of houses delivery system issues the source of houses is obtained;By institute
The second source of houses picture prestored stated in the first source of houses picture and presetting database carries out Characteristic Contrast, is determined according to comparing result
Whether satisfaction prompt manual examination and verification preset condition;If satisfied, then obtaining target second source of houses figure for meeting the preset condition
Piece, and the prompt information that prompt auditor carries out manual examination and verification is generated based on target second source of houses picture;Obtain auditor
The auditing result information of submission determines the final review result of first source of houses picture based on the auditing result information.It is logical
Aforesaid way is crossed, when the source of houses picture uploaded when obtaining user and issuing the source of houses, the first source of houses picture that automatically will currently upload
Characteristic Contrast is carried out with the source of houses picture that prestores that history uploads, after Characteristic Contrast result meets specific preset condition, is just prompted
Manual examination and verification are carried out, realize the audit mode of man-computer cooperation, auditor only need to meet particular preset to automated characterization comparing result
The picture of condition is audited, and when manual examination and verification, there are the target second picture of robber's figure suspicion it has been determined that auditor without
The comparison one by one that magnanimity has source of houses picture need to be carried out, manpower is thus greatly reduced, efficiently identifies and usurp source of houses picture
Situation.
It is the flow diagram of picture examination method second embodiment of the present invention referring to Fig. 3, Fig. 3.
Based on the above embodiment, in the present embodiment, step S20 includes:
Step S50 determines that algorithm determines the condition code and second source of houses of first source of houses picture based on default condition code
The condition code of picture, wherein described document information includes at least informative abstract MD5 code or Color Distribution Features code;
Based on the above embodiment, in the present embodiment, default condition code refers to calculating based on default condition code algorithm
To be used to identify picture unique signature sequence coding, may include informative abstract MD5 code or color characteristic distribution code.It can be with
The informative abstract MD5 code of each picture is calculated separately,
Further, compression processing is carried out to each picture respectively, by picture compression to presetted pixel size, such as 8x8,
Totally 64 pixels determine the corresponding grey parameter of each pixel, calculate the average gray parameter of all 64 pixels, then will be each
The grey parameter of pixel is compared with average gray parameter, is denoted as 1 more than or equal to average gray parameter, is less than average ash
Degree parameter is denoted as 0, to obtain corresponding 64 integers of 64 pixels, loses 64 integers based on specific preset order and carries out
Arrangement, obtains the sub-sequence fingerprint of each picture, i.e. picture color distribution characteristics code.
Step S60 compares the condition code of first source of houses picture and the condition code of the second source of houses picture, determines
The condition code matching degree of first source of houses picture and the second source of houses picture;
For each first source of houses picture, respectively by all second source of houses pictures in the MD5 code of picture and presetting database
MD5 code compared one by one, determine every two comparison picture MD5 code it is whether consistent, if two pictures MD5 code unanimously,
Then determine that corresponding two pictures are identical picture, the matching degree of picture is 100%.If being compared based on MD5 code, then may be used
Only to determine whether the MD5 code of two pictures is completely the same, that is, determine whether condition code matching degree is 100%.
Further, if being compared based on color characteristic distribution code, for each first source of houses picture, by the first room
The Color Distribution Features code of source picture and the Color Distribution Features code of second source of houses pictures all in presetting database are each corresponding
Numerical value in numerical digit is compared one by one, determines that corresponding two picture color distribution characteristics codes correspond to the identical position of numerical value in numerical digit
Several ratios with Color Distribution Features code total bit, using the ratio as the color characteristic code matching degree of two pictures.Similarly
Method can determine the color characteristic distribution code of the second source of houses picture.
Described document information matching degree is compared with default condition code matching degree, judges described document information by step S70
Whether it is greater than or equal to default condition code matching degree with degree;
Default condition code matching degree refer to it is preset, for determining the condition code of prompt manual examination and verification preset condition
Threshold value.
For MD5 code, 100% can be set by default condition code matching degree, if the MD5 code of two pictures is inconsistent,
Then determine that corresponding picture is different pictures, the matching degree of picture non-100%.The preset condition of corresponding prompt manual examination and verification is picture
MD5 code matching degree be 100%, that is, if the MD5 code matching degree of two pictures be 100%, determine comparing result meet prompt
The preset condition of manual examination and verification determines that comparing result is unsatisfactory for prompting if the MD5 code matching degree of two pictures is not 100%
The preset condition of manual examination and verification.For color characteristic distribution code, a color characteristic code matching degree threshold value can be preset, such as
90%, the preset condition of corresponding prompt manual examination and verification can be set as: the color characteristic code matching degree of two pictures is greater than or waits
In pre-set color condition code matching degree threshold value, that is, when the color characteristic code matching degree of two pictures is greater than or equal to pre-set color
When condition code matching degree threshold value, determine that the comparing result of the two pictures meets the preset condition of prompt manual examination and verification;If two
The color characteristic code matching degree of picture is less than pre-set color condition code matching degree threshold value, then determines the comparing result of the two pictures
It is unsatisfactory for the preset condition of prompt manual examination and verification.
Step S80 determines that satisfaction mentions if described document information matching degree is greater than or equal to the default condition code matching degree
Show the preset condition of manual examination and verification;
For MD5 code, 100% can be set by default condition code matching degree, if the MD5 code of two pictures is inconsistent,
Then determine that corresponding picture is different pictures, the matching degree of picture non-100%.The preset condition of corresponding prompt manual examination and verification is picture
MD5 code matching degree be 100%, that is, if the MD5 code matching degree of two pictures be 100%, determine comparing result meet prompt
The preset condition of manual examination and verification determines that comparing result is unsatisfactory for prompting if the MD5 code matching degree of two pictures is not 100%
The preset condition of manual examination and verification.For color characteristic distribution code, a color characteristic code matching degree threshold value can be preset, such as
90%, the preset condition of corresponding prompt manual examination and verification can be set as: the color characteristic code matching degree of two pictures is greater than or waits
In pre-set color condition code matching degree threshold value, that is, when the color characteristic code matching degree of two pictures is greater than or equal to pre-set color
When condition code matching degree threshold value, determine that the comparing result of the two pictures meets the preset condition of prompt manual examination and verification;If two
The color characteristic code matching degree of picture is less than pre-set color condition code matching degree threshold value, then determines the comparing result of the two pictures
It is unsatisfactory for the preset condition of prompt manual examination and verification.
Step S30 includes:
Step S90 obtains target second source of houses picture for meeting the preset condition, and according to second source of houses of target
Picture, first source of houses picture and the matching degree generate the prompt information that prompt auditor carries out manual examination and verification.
Meet prompt manual examination and verification in the comparing result for determining specific first source of houses picture and specific second source of houses picture
Preset condition when, then specific second source of houses picture be target source of houses picture, based on specific first source of houses picture with
And the comparing result (i.e. the matching degree of picture) of specific second source of houses picture and the two pictures, generate prompt auditor into
The prompt information of row manual examination and verification.
In the present embodiment, determine that algorithm determines the condition code and second of first source of houses picture based on default condition code
The condition code of source of houses picture, wherein described document information includes at least informative abstract MD5 code or Color Distribution Features code;It will be described
The condition code of first source of houses picture and the condition code of the second source of houses picture compare, and determine first source of houses picture and second
The condition code matching degree of source of houses picture;Described document information matching degree is compared with default condition code matching degree, described in judgement
Whether condition code matching degree is greater than or equal to default condition code matching degree;If described document information matching degree is greater than or equal to described pre-
If condition code matching degree, then the preset condition for meeting prompt manual examination and verification is determined;Obtain the target for meeting the preset condition
Two source of houses pictures, and generated and prompted according to second source of houses of the target picture, first source of houses picture and the matching degree
The prompt information of auditor's progress manual examination and verification.By the above-mentioned means, realizing that the condition code based on picture accurately determines picture
Matching degree, and meet target second source of houses picture of the preset condition, and according to second source of houses of the target picture, described
One source of houses picture and the matching degree generate the prompt information that prompt auditor carries out manual examination and verification, are based on tool convenient for auditor
His prompt information of body carries out manual examination and verification.
Further, Fig. 4 is the flow diagram of picture examination method 3rd embodiment of the present invention.
Based on the above embodiment, in the present embodiment, step S50 is replaced are as follows:
Step S100, determines the condition code for calculating fixed first source of houses picture based on the default condition code, and from described
The pre-stored characteristics code that the second source of houses picture is obtained in presetting database, using the condition code as the second source of houses picture.
Based on the above embodiment, in the present embodiment, it for every source of houses picture in presetting database, can count in advance
The condition codes such as corresponding MD5 code or color characteristic distribution code are calculated, and in the preset database by the condition code being calculated storage,
And establish the incidence relation of condition code with corresponding second source of houses picture.It is audited to the first source of houses picture that user uploads
When, the condition code of the first source of houses picture is calculated based on identical condition code algorithm, and present count is obtained based on above-mentioned incidence relation
Above-mentioned implementation is based on as the condition code of corresponding second source of houses picture according to the pre-stored characteristics code of second source of houses picture each in library
The comparison checking method of example is audited, to avoid requiring when every time auditing the first source of houses picture to preset data
The second source of houses picture in library calculates condition code, improves to specific efficiency.
Further, Fig. 5 is the flow diagram of picture examination method fourth embodiment of the present invention.
Based on the above embodiment, in the present embodiment, include: after step S40
First source of houses picture and its condition code are stored in institute when auditing result is that audit passes through by step S110
It states in presetting database, and the first source of houses picture being stored in the presetting database is associated with its condition code.
Based on the above embodiment, in the present embodiment, it is had submitted as auditor by the function choosing-item of " audit passes through " careful
When core passes through result information, source of houses delivery system determines that auditing result passes through for audit, by the first source of houses picture and its corresponding MD5
Code or the storage of the condition codes such as color characteristic code in the preset database, and establish being associated with for the first source of houses picture and condition code
System converts the second source of houses picture with upload for the first source of houses picture after picture examination passes through to realize, after being used as
The audit contrast material of the continuous source of houses picture uploaded.
Further, if comparing result is unsatisfactory for the preset condition of prompt manual examination and verification, i.e., corresponding after step S20
The first source of houses picture without carrying out manual examination and verification, which passes through, by the first source of houses picture and its correspondence
The condition codes such as MD5 code or color characteristic code store in the preset database, and establish being associated with for the first source of houses picture and condition code
Relationship.
Further, Fig. 6 is the flow diagram of the 5th embodiment of picture examination method of the present invention.
Based on the above embodiment, in the present embodiment, include: after step S40
Step S120, when auditing result be audit it is obstructed out-of-date, based on first source of houses picture generate audit do not pass through
Prompt information, and the audit is not sent to by prompt information to the user's end for uploading the user of first source of houses picture
End.
Based on the above embodiment, in the present embodiment, if auditor is not submitted by preset audit by function choosing-item
When audit does not pass through auditing result information, source of houses delivery system determines that auditing result does not pass through for audit, and obstructed based on auditing
The first source of houses picture crossed, which generates, audits unacceptable prompt information, then will be prompted to information and be sent to upload first source of houses picture
User user terminal, such as mobile phone, tablet computer or personal computer terminal, login when can be by user's uploading pictures
The identity such as account number determine user or the user terminal of uploading pictures.Further, it is also possible to based on audit unacceptable first
The matching degree of source of houses picture and its corresponding target second source of houses picture and the two, which generates, audits unacceptable prompt information.
In the present embodiment, obstructed out-of-date to audit when auditing result, audit is generated not based on first source of houses picture
By prompt information, and the audit is not sent to the user for uploading the user of first source of houses picture by prompt information
Terminal.To in time by audit unacceptable result feed back to upload source of houses picture user, user is prompted.
Further, Fig. 7 is the flow diagram of picture examination method sixth embodiment of the present invention.Step S20 includes:
Step S130 extracts the characteristic point information of first source of houses picture based on default feature point extraction algorithm;
Based on feature point extraction algorithm, such as SFIT algorithm, SUSAN Corner Detection Algorithm Harries Corner Detection Algorithm
And Forstner feature point detection algorithm extracts the characteristic point of each source of houses picture
Step S140, by the pre-stored characteristics point of the characteristic point information of first source of houses picture and second source of houses picture
Information compares, the matching characteristic point quantity and described first based on first source of houses picture Yu second source of houses picture
The ratio of source of houses picture feature point sum determines the Feature Points Matching degree of first source of houses picture Yu second source of houses picture;
For each first source of houses picture, by the characteristic point of source of houses picture and the characteristic point of the second all source of houses pictures point
Do not compare, determine the source of houses picture with respectively with the characteristic point quantity of each second source of houses picture match and the source of houses picture
The ratio of characteristic point sum, i.e. matching characteristic point ratio, the matching that matching characteristic point ratio is compared between picture as two
Degree.
The Feature Points Matching degree and default Feature Points Matching degree are compared, determine the characteristic point by step S150
Whether matching degree and the default Feature Points Matching degree are greater than or equal to the default Feature Points Matching degree;
It can preset with Feature Points Matching degree threshold value, such as 85%, the preset condition of corresponding prompt manual examination and verification can
With setting are as follows: the Feature Points Matching degree of two pictures is greater than or equal to default Feature Points Matching degree threshold value, that is, when two pictures
When Feature Points Matching degree is greater than or equal to default Feature Points Matching degree threshold value, determine that the comparing result of two pictures meets prompter
The preset condition of work audit;If the Feature Points Matching degree of two pictures is less than default Feature Points Matching degree threshold value, determine this two
The comparing result of a picture is unsatisfactory for the preset condition of prompt manual examination and verification.
Step S160, if so, determining the preset condition for meeting prompt manual examination and verification.
When the Feature Points Matching degree of two pictures is greater than or equal to default Feature Points Matching degree threshold value, two pictures are determined
Comparing result meet prompt manual examination and verification preset condition.Reminding method based on above-mentioned manual examination and verification is prompted, and base
Auditing result is determined in the auditing result information that auditor submits.
In the present embodiment, the characteristic point information of first source of houses picture is extracted based on default feature point extraction algorithm;
The characteristic point information of first source of houses picture and the pre-stored characteristics point information of second source of houses picture are compared, are based on
First source of houses picture and the matching characteristic point quantity of second source of houses picture and first source of houses picture feature point are total
Several ratio determines the Feature Points Matching degree of first source of houses picture Yu second source of houses picture;By the Feature Points Matching
Degree is compared with default Feature Points Matching degree, determines whether the Feature Points Matching degree and the default Feature Points Matching degree are big
In or equal to the default Feature Points Matching degree;If so, determining the preset condition for meeting prompt manual examination and verification.Pass through above-mentioned side
Formula accurately determines audit picture based on picture feature point and has deposited the matching degree of picture, improve picture examination accuracy rate and
Reliability.
Further, Fig. 8 is the flow diagram of the 7th embodiment of picture examination method of the present invention.Based on above-mentioned implementation
Example, in the present embodiment, described document information are Color Distribution Features code, first source of houses picture or second source of houses picture
The determination method of Color Distribution Features code include:
Step S170 is obtained by first source of houses picture or second source of houses picture compression to presetted pixel size
Compressed source of houses picture;
Based on the above embodiment, in the present embodiment, Color Distribution Features code refers to the spy of the distribution of color based on picture
Levy the picture color feature coding extracted.In the present embodiment, the first source of houses picture and the second source of houses picture take identical face
Color distribution characteristics code computational algorithm is calculated, to compare the condition code for determining the first source of houses picture and the second source of houses picture
With degree.In the present embodiment, when calculating the characteristic value of source of houses picture, first picture is compressed, by picture compression to default
Pixel Dimensions.Such as 8x8, totally 64 pixels, minification: by the size of image down to 8*8,64 pixels in total.This
The effect of step is to remove the details of image, only retains the essential informations such as structure/light and shade, abandons different sizes/ratio bring figure
Aberration is different.
Step S180 determines the grey parameter of each pixel and being averaged for grey parameter of compressed source of houses picture
Value;
Based on above-mentioned steps, after obtaining compressed source of houses picture, the corresponding gray scale ginseng of each pixel of source of houses picture is determined
Number, then calculate the average gray parameter of all 64 pixels.
The size comparison result of the grey parameter of each pixel and the average value is determined first room by step S190
The Color Distribution Features code of source picture or second source of houses picture.
The grey parameter of each pixel is compared with average gray parameter again, more than or equal to average gray parameter
It is denoted as 1, is denoted as 0 less than average gray parameter, so that corresponding 64 integers of 64 pixels are obtained, it is suitable based on specifically presetting
64 integers of ordered pair are arranged, and the sub-sequence fingerprint of each picture, i.e. picture color distribution characteristics code are obtained.
Further, all second source of houses pictures can also be compressed in advance, boil down to is greater than the size of 8X8, example
Such as 32X32, gray scale picture is converted by compressed second source of houses picture, then discrete cosine transform is carried out to picture, is obtained
DCT coefficient matrix retains the data matrix of upper left corner 8*8, calculates and retains DCT mean value in 8*8 matrix, is arranged 64 s' of 0 or 1
Hash value, more than or equal to being set as DCT mean value " 1 " is set as " 0 " less than DCT mean value.It combines, just constitutes one
64 integers, here it is the fingerprints of this picture.When obtaining the first source of houses picture, the first source of houses picture is carried out same
Operation, obtains the fingerprint of the first source of houses picture, the fingerprint of the first source of houses picture and the fingerprint of the second source of houses picture is compared,
The ratio for determining identical data, using the ratio as the similarity of the first source of houses picture and the second source of houses picture.
In the present embodiment, by first source of houses picture or second source of houses picture compression to presetted pixel size,
Obtain compressed source of houses picture;Determine the grey parameter of each pixel of compressed source of houses picture and putting down for grey parameter
Mean value;The size comparison result of the grey parameter of each pixel and the average value is determined into first source of houses picture or described
The Color Distribution Features code of second source of houses picture.By the above-mentioned means, the Color Distribution Features code based on picture accurately determines
Audit picture and the matching degree for having deposited picture, improve the accuracy rate and reliability of picture examination.
In addition, the embodiment of the present invention also provides a kind of picture examination device.
It is the functional block diagram of picture examination device first embodiment of the present invention referring to Fig. 9, Fig. 9.
In the present embodiment, the picture examination device includes:
First obtains module 10, the first source of houses figure uploaded for obtaining user when source of houses delivery system issues the source of houses
Piece;
Contrast module 20 carries out the second source of houses picture prestored in first source of houses picture and presetting database special
Sign comparison determines whether the preset condition for meeting prompt manual examination and verification according to comparing result;
First generation module 30, for meeting target second source of houses picture of the preset condition if satisfied, then obtaining, and
The prompt information that prompt auditor carries out manual examination and verification is generated based on target second source of houses picture;
Second obtains module 40, for obtaining the auditing result information of auditor's submission, is based on the auditing result information
Determine the final review result of first source of houses picture.
Wherein, each virtual functions module of above-mentioned picture examination device is stored in the storage of picture examination equipment shown in Fig. 1
It is functional for realizing the institute of picture examination program in device 1005;When each module is executed by processor 1001, improves identification and usurp
The efficiency of source of houses picture.
Further, the contrast module is also used to:
Determine that algorithm determines the condition code of first source of houses picture and the spy of the second source of houses picture based on default condition code
Levy code, wherein described document information includes at least informative abstract MD5 code or Color Distribution Features code;
The condition code of first source of houses picture and the condition code of the second source of houses picture are compared, determine described first
The condition code matching degree of source of houses picture and the second source of houses picture;
Described document information matching degree is compared with default condition code matching degree, whether judges described document information matching degree
More than or equal to default condition code matching degree;
If described document information matching degree is greater than or equal to the default condition code matching degree, determine that meeting prompt manually examines
The preset condition of core;
The generation module is also used to:
Target second source of houses picture for meeting the preset condition is obtained, and according to second source of houses of the target picture, institute
It states the first source of houses picture and the matching degree generates the prompt information that prompt auditor carries out manual examination and verification.
Further, the contrast module is also used to:
Determine the condition code for calculating fixed first source of houses picture based on the default condition code, and from the presetting database
The middle pre-stored characteristics code for obtaining the second source of houses picture, using the condition code as the second source of houses picture.
Further, the picture examination device further include:
Memory module, for when auditing result is that audit passes through, first source of houses picture and its condition code to be stored
It is closed in the presetting database, and by the first source of houses picture being stored in the presetting database with its condition code
Connection.
Further, the picture examination device further include:
Second generation module is generated based on first source of houses picture and is examined for being that audit is obstructed out-of-date when auditing result
Core does not pass through prompt information, and the audit is not sent to the user's for uploading first source of houses picture by prompt information
User terminal.
Further, the contrast module is also used to:
The characteristic point information of first source of houses picture is extracted based on default feature point extraction algorithm;
The pre-stored characteristics point information of the characteristic point information of first source of houses picture and second source of houses picture is carried out
Comparison, matching characteristic point quantity and first source of houses picture based on first source of houses picture and second source of houses picture
The ratio of characteristic point sum determines the Feature Points Matching degree of first source of houses picture Yu second source of houses picture;
The Feature Points Matching degree and default Feature Points Matching degree are compared, determine the Feature Points Matching degree and institute
State whether default Feature Points Matching degree is greater than or equal to the default Feature Points Matching degree;
If so, determining the preset condition for meeting prompt manual examination and verification.
Further, the picture examination device further includes color characteristic code determining module, is used for:
By first source of houses picture or second source of houses picture compression to presetted pixel size, compressed room is obtained
Source picture;
Determine the grey parameter of each pixel of compressed source of houses picture and the average value of grey parameter;
By the size comparison result of the grey parameter of each pixel and the average value determine first source of houses picture or
The Color Distribution Features code of second source of houses picture.
In addition, the embodiment of the present invention also provides a kind of computer readable storage medium.
Picture examination program is stored on computer readable storage medium of the present invention, wherein the picture examination program is located
When managing device execution, realize such as the step of above-mentioned picture examination method.
Wherein, picture examination program, which is performed realized method, can refer to each reality of picture examination method of the present invention
Example is applied, details are not described herein again.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of picture examination method, which is characterized in that the picture examination method includes:
Obtain the first source of houses picture that user uploads when source of houses delivery system issues the source of houses;
The second source of houses picture prestored in first source of houses picture and presetting database is subjected to Characteristic Contrast, according to comparison
As a result determine whether the preset condition for meeting prompt manual examination and verification;
If satisfied, then obtaining target second source of houses picture for meeting the preset condition, and it is based on second source of houses of the target figure
Piece generates the prompt information that prompt auditor carries out manual examination and verification;
The auditing result information that auditor submits is obtained, first source of houses picture is determined most based on the auditing result information
Whole auditing result.
2. picture examination method as described in claim 1, which is characterized in that described by first source of houses picture and present count
Characteristic Contrast is carried out according to the second source of houses picture prestored in library, is determined whether to meet prompt manual examination and verification according to comparing result
The step of preset condition includes:
Determine that algorithm determines the condition code of first source of houses picture and the condition code of the second source of houses picture based on default condition code,
Wherein, described document information includes at least informative abstract MD5 code or Color Distribution Features code;
The condition code of first source of houses picture and the condition code of the second source of houses picture are compared, determine first source of houses
The condition code matching degree of picture and the second source of houses picture;
Described document information matching degree is compared with default condition code matching degree, judges whether described document information matching degree is greater than
Or it is equal to default condition code matching degree;
If described document information matching degree is greater than or equal to the default condition code matching degree, determine to meet prompt manual examination and verification
Preset condition;
It is described to obtain target second source of houses picture for meeting the preset condition, and generated based on target second source of houses picture
Prompt auditor carry out manual examination and verification prompt information the step of include:
It obtains and meets target second source of houses picture of the preset condition, and according to second source of houses of the target picture, described the
One source of houses picture and the matching degree generate the prompt information that prompt auditor carries out manual examination and verification.
3. picture examination method as claimed in claim 2, which is characterized in that described to determine that algorithm determines based on default condition code
The step of condition code of first source of houses picture and the condition code of the second source of houses picture, replaces are as follows:
The condition code for calculating fixed first source of houses picture is determined based on the default condition code, and is obtained from the presetting database
The pre-stored characteristics code for taking the second source of houses picture, using the condition code as the second source of houses picture.
4. picture examination method as claimed in claim 2 or claim 3, which is characterized in that the base is based on the auditing result information
Include: after the step of determining the final review result of first source of houses picture
When auditing result is that audit passes through, first source of houses picture and its condition code are stored in the presetting database
In, and the first source of houses picture being stored in the presetting database is associated with its condition code.
5. picture examination method as described in claim 1, which is characterized in that described to determine institute based on the auditing result information
Include: after the step of stating the final review result of the first source of houses picture
When auditing result is that audit is obstructed out-of-date, based on first source of houses picture generation audit not by prompt information, and by
The audit is not sent to the user terminal for uploading the user of first source of houses picture by prompt information.
6. picture examination method as described in claim 1, which is characterized in that described by first source of houses picture and present count
Characteristic Contrast is carried out according to the second source of houses picture prestored in library, is determined whether to meet prompt manual examination and verification according to comparing result
The step of preset condition includes:
The characteristic point information of first source of houses picture is extracted based on default feature point extraction algorithm;
The characteristic point information of first source of houses picture and the pre-stored characteristics point information of second source of houses picture are compared,
Matching characteristic point quantity and first source of houses picture feature based on first source of houses picture and second source of houses picture
The ratio of point sum determines the Feature Points Matching degree of first source of houses picture Yu second source of houses picture;
The Feature Points Matching degree and default Feature Points Matching degree are compared, determine the Feature Points Matching degree with it is described pre-
If whether Feature Points Matching degree is greater than or equal to the default Feature Points Matching degree;
If so, determining the preset condition for meeting prompt manual examination and verification.
7. picture examination method as claimed in claim 2, which is characterized in that described document information is Color Distribution Features code, institute
The determination method for stating the Color Distribution Features code of the first source of houses picture or second source of houses picture includes:
By first source of houses picture or second source of houses picture compression to presetted pixel size, compressed source of houses figure is obtained
Piece;
Determine the grey parameter of each pixel of compressed source of houses picture and the average value of grey parameter;
The size comparison result of the grey parameter of each pixel and the average value is determined into first source of houses picture or described
The Color Distribution Features code of second source of houses picture.
8. a kind of picture examination device, which is characterized in that the picture examination device includes:
First obtains module, the first source of houses picture uploaded for obtaining user when source of houses delivery system issues the source of houses;
The second source of houses picture prestored in first source of houses picture and presetting database is carried out feature pair by contrast module
Than determining whether the preset condition for meeting prompt manual examination and verification according to comparing result;
First generation module for meeting target second source of houses picture of the preset condition if satisfied, then obtaining, and is based on institute
It states target second source of houses picture and generates the prompt information that prompt auditor carries out manual examination and verification;
Second obtains module, for obtaining the auditing result information of auditor's submission, determines institute based on the auditing result information
State the final review result of the first source of houses picture.
9. a kind of picture examination equipment, which is characterized in that the picture examination equipment includes processor, memory and storage
On the memory and the picture examination program that can be executed by the processor, wherein the picture examination program is by the place
When managing device and executing, the step of realizing picture examination method as described in any one of claims 1 to 7.
10. a kind of computer readable storage medium, which is characterized in that be stored with picture on the computer readable storage medium and examine
Core program, wherein realizing the figure as described in any one of claims 1 to 7 when the picture examination program is executed by processor
The step of piece checking method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910200477.7A CN110083733A (en) | 2019-03-16 | 2019-03-16 | Picture examination method, apparatus, equipment and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910200477.7A CN110083733A (en) | 2019-03-16 | 2019-03-16 | Picture examination method, apparatus, equipment and computer readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110083733A true CN110083733A (en) | 2019-08-02 |
Family
ID=67412511
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910200477.7A Pending CN110083733A (en) | 2019-03-16 | 2019-03-16 | Picture examination method, apparatus, equipment and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110083733A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111311358A (en) * | 2020-01-20 | 2020-06-19 | 北京无限光场科技有限公司 | Information processing method and device and electronic equipment |
CN111737599A (en) * | 2020-05-07 | 2020-10-02 | 北京城市网邻信息技术有限公司 | Method and device for verifying house source object |
CN111767422A (en) * | 2020-06-30 | 2020-10-13 | 平安国际智慧城市科技股份有限公司 | Data auditing method, device, terminal and storage medium |
CN113425319A (en) * | 2020-03-08 | 2021-09-24 | 广东毓秀科技有限公司 | Respiratory system disease intelligent auxiliary diagnosis decision-making method for basic medical institution |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101996180A (en) * | 2009-08-12 | 2011-03-30 | 升东网络科技发展(上海)有限公司 | Picture examination and filter system and method |
CN107133221A (en) * | 2017-06-09 | 2017-09-05 | 北京京东尚科信息技术有限公司 | Signal auditing method, device, computer-readable medium and electronic equipment |
CN107688824A (en) * | 2017-07-27 | 2018-02-13 | 平安科技(深圳)有限公司 | Picture match method and terminal device |
CN108416066A (en) * | 2018-03-29 | 2018-08-17 | 平安好房(上海)电子商务有限公司 | Image searching method, user equipment, storage medium and picture searching device |
CN108734393A (en) * | 2018-05-14 | 2018-11-02 | 平安好房(上海)电子商务有限公司 | Matching process, user equipment, storage medium and the device of information of real estate |
CN108763570A (en) * | 2018-06-05 | 2018-11-06 | 北京拓世寰宇网络技术有限公司 | A kind of method and device identifying the identical source of houses |
CN108875757A (en) * | 2017-05-08 | 2018-11-23 | 腾讯科技(深圳)有限公司 | A kind of signal auditing method, server and system |
CN109284894A (en) * | 2018-08-10 | 2019-01-29 | 广州虎牙信息科技有限公司 | Picture examination method, apparatus, storage medium and computer equipment |
-
2019
- 2019-03-16 CN CN201910200477.7A patent/CN110083733A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101996180A (en) * | 2009-08-12 | 2011-03-30 | 升东网络科技发展(上海)有限公司 | Picture examination and filter system and method |
CN108875757A (en) * | 2017-05-08 | 2018-11-23 | 腾讯科技(深圳)有限公司 | A kind of signal auditing method, server and system |
CN107133221A (en) * | 2017-06-09 | 2017-09-05 | 北京京东尚科信息技术有限公司 | Signal auditing method, device, computer-readable medium and electronic equipment |
CN107688824A (en) * | 2017-07-27 | 2018-02-13 | 平安科技(深圳)有限公司 | Picture match method and terminal device |
WO2019019595A1 (en) * | 2017-07-27 | 2019-01-31 | 平安科技(深圳)有限公司 | Image matching method, electronic device method, apparatus, electronic device and medium |
CN108416066A (en) * | 2018-03-29 | 2018-08-17 | 平安好房(上海)电子商务有限公司 | Image searching method, user equipment, storage medium and picture searching device |
CN108734393A (en) * | 2018-05-14 | 2018-11-02 | 平安好房(上海)电子商务有限公司 | Matching process, user equipment, storage medium and the device of information of real estate |
CN108763570A (en) * | 2018-06-05 | 2018-11-06 | 北京拓世寰宇网络技术有限公司 | A kind of method and device identifying the identical source of houses |
CN109284894A (en) * | 2018-08-10 | 2019-01-29 | 广州虎牙信息科技有限公司 | Picture examination method, apparatus, storage medium and computer equipment |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111311358A (en) * | 2020-01-20 | 2020-06-19 | 北京无限光场科技有限公司 | Information processing method and device and electronic equipment |
CN111311358B (en) * | 2020-01-20 | 2023-05-30 | 北京有竹居网络技术有限公司 | Information processing method and device and electronic equipment |
CN113425319A (en) * | 2020-03-08 | 2021-09-24 | 广东毓秀科技有限公司 | Respiratory system disease intelligent auxiliary diagnosis decision-making method for basic medical institution |
CN111737599A (en) * | 2020-05-07 | 2020-10-02 | 北京城市网邻信息技术有限公司 | Method and device for verifying house source object |
CN111767422A (en) * | 2020-06-30 | 2020-10-13 | 平安国际智慧城市科技股份有限公司 | Data auditing method, device, terminal and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110083733A (en) | Picture examination method, apparatus, equipment and computer readable storage medium | |
CN109165940B (en) | Anti-theft method and device and electronic equipment | |
US20200065471A1 (en) | Security verification method and relevant device | |
CN107430654A (en) | Switch biological characteristic authentication | |
CN108510233A (en) | Long-range face label match attend a banquet method, electronic device and computer readable storage medium | |
Saboia et al. | Eye specular highlights telltales for digital forensics: A machine learning approach | |
CN109815970B (en) | Method and device for identifying copied image, computer equipment and storage medium | |
WO2019200737A1 (en) | Real estate data uploading method and apparatus, computer device, and storage medium | |
CN110929063A (en) | Album generating method, terminal device and computer readable storage medium | |
CN111476269A (en) | Method, device, equipment and medium for constructing balanced sample set and identifying copied image | |
US20160110531A1 (en) | Information processing apparatus, terminal apparatus and information processing method | |
CN112306829A (en) | Method and device for determining performance information, storage medium and terminal | |
CN109636566A (en) | Method for exhibiting data, device, equipment and computer readable storage medium | |
CN108270789A (en) | Internetbank activating method, equipment, system and computer readable storage medium | |
CN113792661A (en) | Image detection method, image detection device, electronic equipment and storage medium | |
CN108922068A (en) | A kind of information processing method and its equipment, storage medium, electronic equipment | |
CN109446778A (en) | Immovable Property Registration information acquisition method, computer installation and computer readable storage medium based on recognition of face | |
CN112182520B (en) | Identification method and device of illegal account number, readable medium and electronic equipment | |
CN108446737B (en) | Method and device for identifying objects | |
CN111179023A (en) | Order identification method and device | |
CN112637635A (en) | File security method and system, computer readable storage medium and processor | |
CN111680191A (en) | Information display method, device, equipment and storage device | |
CN109544325A (en) | Switching method, device and the computer equipment of face label system based on data processing | |
CN111382408A (en) | Intelligent user identification method and device and computer readable storage medium | |
CN110415128A (en) | Policy information management method, device, equipment and computer readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190802 |
|
WD01 | Invention patent application deemed withdrawn after publication |