CN108921209A - Image identification method, device and electronic equipment - Google Patents
Image identification method, device and electronic equipment Download PDFInfo
- Publication number
- CN108921209A CN108921209A CN201810647364.7A CN201810647364A CN108921209A CN 108921209 A CN108921209 A CN 108921209A CN 201810647364 A CN201810647364 A CN 201810647364A CN 108921209 A CN108921209 A CN 108921209A
- Authority
- CN
- China
- Prior art keywords
- feature vector
- picture
- pixel
- fusion feature
- identified
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The present embodiments relate to technical field of image processing, in particular to a kind of image identification method, device and electronic equipment.This method includes obtaining multiple pixels that picture to be identified and the picture to be identified include in real time, for each pixel in multiple pixels, judge whether the pixel is characterized a little, if the pixel is characterized a little, extract the feature vector of the pixel, the each feature vector extracted is merged to obtain fusion feature vector, by fusion feature vector input training apparatus, the fusion feature vector is compared with default original image fusion feature vector by identification using the training aids, obtain similarity ratio value, judge whether similarity ratio value is less than default similarity and defines value, if being less than, send prompt information, fraud region is marked in picture to be identified.This method can be improved the recognition accuracy to fraud picture.
Description
Technical field
The present embodiments relate to technical field of image processing, in particular to a kind of image identification method, device and
Electronic equipment.
Background technique
With the development of information technology, more and more working processes are handled by internet, for some needs
The business of uploading pictures data, it is understood that there may be client submits the case where fraud picture information.In order to avoid this kind of situation,
It needs to carry out true and false judgement and identification to the picture information that client submits.
But the existing picture information submitted to client carries out knowledge method for distinguishing leans on artificial micro-judgment mostly, for faking
Horizontal higher picture, it is difficult to which realization accurately identifies and judges.
Summary of the invention
In view of this, can be improved the present invention provides a kind of image identification method, device and electronic equipment to fraud figure
The recognition accuracy of piece.
To achieve the above object, the embodiment of the invention provides a kind of image identification method, the method includes：
Multiple pixels that picture to be identified and the picture to be identified include are obtained in real time；
For each pixel in the multiple pixel, judge whether the pixel is characterized a little, if the pixel
It is characterized the feature vector for a little extracting the pixel, each feature vector extracted is merged to obtain fusion feature
Vector；
By the fusion feature vector input training apparatus, wherein the training aids prestore original image fusion feature to
Amount；The fusion feature vector is compared with the original image fusion feature vector by identification using the training aids, is obtained
Obtain similarity ratio value；
Judge whether the similarity ratio value is less than default similarity and defines value, if the similarity ratio value is less than institute
It states default similarity and defines value, send and determine that the picture to be identified is the prompt of fraud picture, extract the fusion feature
In vector at least one unmatched feature vector of the original image fusion feature vector, will at least one described feature to
Corresponding pixel is measured to mark in the picture to be identified.
Optionally, the method also includes：
At least one described feature vector is inputted into the training aids；
Second training is carried out to the training aids.
Optionally, judge the step of whether pixel is characterized, including：
Obtain the Hessian matrix of the pixel；
The Hessian matrix and box filter are subjected to convolution, obtain the multiple black plug responses and the picture of the pixel
The picture pyramid of vegetarian refreshments, wherein the picture pyramid includes multilayer, and each black plug response and each layer correspond；
For every layer in the picture pyramid, judge this layer of corresponding black plug response this layer, this layer upper one
Whether it is most to be worth in next layer of multiple neighborhood points of layer and this layer, if being most worth, determines that the pixel is characterized a little.
Optionally, the training aids is convolutional neural networks training aids.
Optionally, the method also includes：
It obtains and modifies the modification instruction that the default similarity defines value；
Value is defined to the default similarity according to modification instruction to modify.
The embodiment of the invention also provides a kind of picture recognition devices, including：
Obtain module, the multiple pixels for including for obtaining picture to be identified and the picture to be identified in real time；
Characteristic point judgment module, for whether judging the pixel for each pixel in the multiple pixel
It is characterized a little, if the pixel is characterized the feature vector for a little extracting the pixel, each feature vector extracted is carried out
Fusion is to obtain fusion feature vector；
Similarity ratio value obtains module, by the fusion feature vector input training apparatus, wherein the training aids prestores
There is original image fusion feature vector；Using the training aids by the fusion feature vector and the original image fusion feature
Identification is compared in vector, obtains similarity ratio value；
Judgment module defines value for judging whether the similarity ratio value is less than default similarity, if described similar
Degree ratio value is less than the default similarity and defines value, sends and determines that the picture to be identified for the prompt of fraud picture, extracts
It, will be described out at least one unmatched feature vector of the original image fusion feature vector in the fusion feature vector
The corresponding pixel of at least one feature vector marks in the picture to be identified.
Optionally, described device further includes second training module；
The second training module is used at least one described feature vector inputting the training aids；To the training aids
Carry out second training.
Optionally, described device further includes modified module；
The modified module, which is used to obtain, modifies the modification instruction that the default similarity defines value, is referred to according to the modification
Order defines value to the default similarity and modifies.
The embodiment of the invention also provides a kind of electronic equipment, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, the processor realize that above-mentioned picture is known when executing the computer program
Other method.
The embodiment of the invention also provides a kind of computer readable storage medium, the readable storage medium storing program for executing includes computer
Program, the electronic equipment computer program controls the readable storage medium storing program for executing when running where execute above-mentioned picture recognition side
Method.
Image identification method, device and electronic equipment provided in an embodiment of the present invention, by by the fusion of picture to be identified
Feature vector is compared with original image fusion feature vector obtains similarity ratio value, according to similarity ratio value and presets
The size that similarity defines value relatively picks out whether picture to be identified is fraud picture, improves the standard of the identification to fraud picture
Exactness.
Further, this method also marks the corresponding region of the feature vector of fraud, is convenient for subsequent analysis.
Further, this method carries out second training to training aids, realizes also by the feature vector input training apparatus of fraud
Optimization to training aids improves subsequent recognition efficiency, shortens recognition time.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is the block diagram of a kind of electronic equipment 10 provided by the embodiment of the present invention.
Fig. 2 is a kind of flow chart of image identification method provided by the embodiment of the present invention.
Fig. 3 is the schematic diagram for the sub-step that step S22 shown in Fig. 2 includes in an embodiment.
Fig. 4 is a kind of module frame chart of picture recognition device 20 provided by the embodiment of the present invention.
Icon：10- electronic equipment；11- memory；12- processor；13- network module；20- picture recognition device；21-
Obtain module；22- characteristic point judgment module；23- similarity ratio value obtains module；24- judgment module.
Specific embodiment
With the development of information technology, more and more working processes are handled by internet, for some needs
The business of uploading pictures data, it is understood that there may be client submits the case where fraud picture information.In order to avoid this kind of situation,
It needs to carry out true and false judgement and identification to the picture information that client submits.
Further investigation reveals that the existing picture information submitted to client carries out knowledge method for distinguishing leans on artificial micro-judgment mostly,
For horizontal higher picture of faking, it is difficult to which realization accurately identifies and judges.
Defect present in the above scheme in the prior art, is that inventor is obtaining after practicing and carefully studying
As a result, therefore, the solution that the discovery procedure of the above problem and the hereinafter embodiment of the present invention are proposed regarding to the issue above
Scheme all should be the contribution that inventor makes the present invention in process of the present invention.
Based on the studies above, the embodiment of the invention provides a kind of image identification method, device and electronic equipment, Neng Gouti
Recognition accuracy of the height to fraud picture.
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment only
It is a part of the embodiments of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings
The component of embodiment can be arranged and be designed with a variety of different configurations.
Therefore, the detailed description of the embodiment of the present invention provided in the accompanying drawings is not intended to limit below claimed
The scope of the present invention, but be merely representative of selected embodiment of the invention.Based on the embodiments of the present invention, this field is common
Technical staff's every other embodiment obtained without creative efforts belongs to the model that the present invention protects
It encloses.
It should be noted that：Similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.
Fig. 1 shows the block diagram of a kind of electronic equipment 10 provided by the embodiment of the present invention.The embodiment of the present invention
In electronic equipment 10 can for data storage, transmission, processing function server-side, as shown in Figure 1, electronic equipment 10 wrap
It includes：Memory 11, processor 12, network module 13 and picture recognition device 20.
It is directly or indirectly electrically connected between memory 11, processor 12 and network module 13, to realize the biography of data
Defeated or interaction.It is electrically connected for example, these elements can be realized from each other by one or more communication bus or signal wire.
Picture recognition device 20 is stored in memory 11, the picture recognition device 20 includes at least one can be with software or firmware
(firmware) form is stored in the software function module in the memory 11, and the processor 12 is stored in by operation
The picture recognition device 20 in software program and module, such as the embodiment of the present invention in memory 11, thereby executing various
Functional application and data processing, i.e. image identification method in the realization embodiment of the present invention.
Wherein, the memory 11 may be, but not limited to, random access memory (Random Access Memory,
RAM), read-only memory (Read Only Memory, ROM), programmable read only memory (Programmable Read-Only
Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only Memory, EPROM),
Electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only Memory, EEPROM) etc..
Wherein, memory 11 is for storing program, and the processor 12 executes described program after receiving and executing instruction.
The processor 12 may be a kind of IC chip, the processing capacity with data.Above-mentioned processor 12
It can be general processor, including central processing unit (Central Processing Unit, CPU), network processing unit
(Network Processor, NP) etc..It may be implemented or execute each method, step disclosed in the embodiment of the present invention and patrol
Collect block diagram.General processor can be microprocessor or the processor is also possible to any conventional processor etc..
Network module 13 is used to establish the communication connection between electronic equipment 10 and other communication terminal devices by network,
Realize the transmitting-receiving operation of network signal and data.Above-mentioned network signal may include wireless signal or wire signal.
It is appreciated that structure shown in FIG. 1 is only to illustrate, electronic equipment 10 may also include it is more than shown in Fig. 1 or
Less component, or with the configuration different from shown in Fig. 1.Each component shown in Fig. 1 can using hardware, software or its
Combination is realized.
The embodiment of the present invention also provides a kind of computer readable storage medium, and the readable storage medium storing program for executing includes computer journey
Sequence.Electronic equipment 10 computer program controls the readable storage medium storing program for executing when running where executes following picture recognition side
Method.
Fig. 2 shows a kind of flow charts of image identification method provided by the embodiment of the present invention.The method is related
Method and step defined in process is applied to electronic equipment 10, can be realized by the processor 12.It below will be to shown in Fig. 2
Detailed process is described in detail：
Step S21 obtains multiple pixels that picture to be identified and the picture to be identified include in real time.
For example, obtaining multiple pixel X1, X2 ... the Xn for including in picture P to be identified and picture P to be identified.
Step S22 judges whether the pixel is characterized a little for each pixel in multiple pixels, if the picture
Vegetarian refreshments is characterized the feature vector for a little extracting the pixel, and each feature vector extracted is merged to be merged
Feature vector.
Fig. 3 is please referred to, is enumerated in the present embodiment by step S221, step S222, step S223 and step S224
One of implementation of step S22.
Step S221 obtains the Hessian matrix of the pixel.
For example, obtaining the Hessian matrix of pixel Xi, wherein i ∈ [1, n] ∩ Z.
Hessian matrix and box filter are carried out convolution by step S222, obtain multiple black plug responses of the pixel with
And the picture pyramid of the pixel, wherein picture pyramid includes multilayer, and each black plug response and each layer correspond.
For example, picture pyramid includes 10 layers, every layer of correspondence one black plug response.
Step S223 judges this layer of corresponding black plug response in this layer, this layer for every layer in picture pyramid
Whether it is most to be worth in next layer of multiple neighborhood points of upper one layer and this layer, if being most worth, determines that the pixel is characterized a little.
For example, be directed to the pyramidal third layer of picture, judge the black plug response of third layer in this layer, the second layer and the
Whether it is maximum value or minimum value in four layers of multiple neighborhood points, if maximum value or minimum value, determines that the pixel is characterized
Point.
In another example the neighborhood point quantity of this layer can be eight, the neighborhood point of the second layer can be nine, the 4th layer of neighbour
Domain point can be nine.
Step S224 extracts the feature vector of the pixel, and each feature vector extracted is merged to obtain
Fusion feature vector.
For example, extracting the feature vector of Xi, all feature vectors extracted are subjected to fusion and obtain fusion feature vector.
Step S23, by fusion feature vector input training apparatus, using training aids by the fusion feature vector with prestore
Identification is compared in original image fusion feature vector, obtains similarity ratio value.
Wherein, original image fusion feature vector is prestored in training aids and similarity defines value.
Step S24, judges whether similarity ratio value is less than default similarity and defines value, is carried out according to judging result corresponding
Operation.
For example, sending if similarity ratio value is less than default similarity and defines value and determining that picture to be identified is fraud picture
Prompt, extract in fusion feature vector at least one unmatched feature vector of original image fusion feature vector, will
The corresponding pixel of at least one feature vector marks in picture to be identified.
Optionally, at least one feature vector input training apparatus can be carried out second training to training aids, such as by this method
This setting, can optimize training aids, improve subsequent recognition efficiency, shorten recognition time, for example, if subsequent fraud
The fraud region (feature vector) of picture is matched with the fraud feature vector that training aids stores, and training aids can quickly recognize
The fraud region (feature vector) of subsequent fraud picture.
In the present embodiment, training aids is convolutional neural networks training aids.
Optionally, this method, which can also obtain, modifies the modification instruction that default similarity defines value, according to modification instruction pair
Default similarity defines value and modifies.So set, control can be carried out to the Stringency for identification of faking.
On the basis of the above, as shown in figure 4, the embodiment of the invention provides a kind of picture recognition device 20, the picture
Identification device 20 includes：It obtains module 21, characteristic point judgment module 22, similarity ratio value and obtains module 23 and judgment module
24。
Obtain module 21, the multiple pixels for including for obtaining picture to be identified and the picture to be identified in real time.
It is similar with the realization principle of step S21 in Fig. 2 due to obtaining module 21, do not illustrate more herein.
Characteristic point judgment module 22, for judging that the pixel is for each pixel in the multiple pixel
It is no to be characterized a little, if the pixel is characterized the feature vector for a little extracting the pixel, by each feature vector extracted into
Row fusion is to obtain fusion feature vector.
Since characteristic point judgment module 22 is similar with the realization principle of step S22 in Fig. 2, do not say more herein
It is bright.
Similarity ratio value obtains module 23, is used for the fusion feature vector input training apparatus, wherein the training
Device prestores original image fusion feature vector；The fusion feature vector and the original image are melted using the training aids
It closes feature vector and identification is compared, obtain similarity ratio value.
Since similarity ratio value acquisition module 23 is similar with the realization principle of step S23 in Fig. 2, do not make herein more
More explanations.
Judgment module 24 defines value for judging whether the similarity ratio value is less than default similarity, if the phase
It is less than the default similarity like degree ratio value and defines value, sends and determine that the picture to be identified is the prompt of fraud picture, mention
Take out in the fusion feature vector at least one unmatched feature vector of the original image fusion feature vector, by institute
The corresponding pixel of at least one feature vector is stated to mark in the picture to be identified.
Since judgment module 24 is similar with the realization principle of step S24 in Fig. 2, do not illustrate more herein.
Optionally, which further includes second training module and modified module, wherein second training module
For at least one described feature vector to be inputted the training aids, second training is carried out to the training aids.Modified module is used
In obtaining the modification instruction modified the default similarity and define value, the default similarity is defined according to modification instruction
Value is modified.
To sum up, image identification method, device provided by the embodiment of the present invention and electronic equipment, by fusion feature to
Amount is identified, can be improved the recognition accuracy to fraud picture.
Further, this method also marks the corresponding region of the feature vector of fraud, is convenient for subsequent analysis.
Further, this method carries out second training to training aids, realizes also by the feature vector input training apparatus of fraud
Optimization to training aids improves subsequent recognition efficiency, shortens recognition time.
In several embodiments provided by the embodiment of the present invention, it should be understood that disclosed device and method, it can also
To realize by another way.Device and method embodiment described above is only schematical, for example, in attached drawing
Flow chart and block diagram show that the devices of multiple embodiments according to the present invention, method and computer program product are able to achieve
Architecture, function and operation.In this regard, each box in flowchart or block diagram can represent module, a program
A part of section or code, a part of the module, section or code include that one or more is patrolled for realizing defined
Collect the executable instruction of function.It should also be noted that in some implementations as replacement, function marked in the box
It can occur in a different order than that indicated in the drawings.For example, two continuous boxes can actually be held substantially in parallel
Row, they can also be executed in the opposite order sometimes, and this depends on the function involved.It is also noted that block diagram and/or
The combination of each box in flow chart and the box in block diagram and or flow chart, can the function as defined in executing or dynamic
The dedicated hardware based system made is realized, or can be realized using a combination of dedicated hardware and computer instructions.
In addition, each functional module in each embodiment of the present invention can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, electronic equipment 10 or the network equipment etc.) execute all or part of step of each embodiment the method for the present invention
Suddenly.And storage medium above-mentioned includes：USB flash disk, read-only memory (ROM, Read-Only Memory), is deposited mobile hard disk at random
The various media that can store program code such as access to memory (RAM, Random Access Memory), magnetic or disk.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to the packet of nonexcludability
Contain, so that the process, method, article or equipment for including a series of elements not only includes those elements, but also including
Other elements that are not explicitly listed, or further include for elements inherent to such a process, method, article, or device.
In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including the element
Process, method, article or equipment in there is also other identical elements.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of image identification method, which is characterized in that including：
Multiple pixels that picture to be identified and the picture to be identified include are obtained in real time；
For each pixel in the multiple pixel, judge whether the pixel is characterized a little, if the pixel is spy
Point is levied, the feature vector of the pixel is extracted, each feature vector extracted is merged to obtain fusion feature vector；
By the fusion feature vector input training apparatus, wherein the training aids prestores original image fusion feature vector；It adopts
Identification is compared with the original image fusion feature vector for the fusion feature vector with the training aids, is obtained similar
Spend ratio value；
Judge whether the similarity ratio value is less than default similarity and defines value, if the similarity ratio value is less than described pre-
If similarity defines value, sends and determine that the picture to be identified is the prompt of fraud picture, extract the fusion feature vector
In at least one unmatched feature vector of the original image fusion feature vector, will at least one described feature vector pair
The pixel answered marks in the picture to be identified.
2. image identification method according to claim 1, which is characterized in that the method also includes：
At least one described feature vector is inputted into the training aids；
Second training is carried out to the training aids.
3. image identification method according to claim 1, which is characterized in that judge whether the pixel is characterized step a little
Suddenly, including：
Obtain the Hessian matrix of the pixel；
The Hessian matrix and box filter are subjected to convolution, obtain the multiple black plug responses and the pixel of the pixel
Picture pyramid, wherein the picture pyramid includes multilayer, and each black plug response and each layer correspond；
For every layer in the picture pyramid, judge this layer of corresponding black plug response this layer, upper one layer of this layer with
And in multiple neighborhood points of next layer of this layer whether be most to be worth, if being most worth, determine that the pixel is characterized a little.
4. image identification method according to claim 1, which is characterized in that the training aids is convolutional neural networks training
Device.
5. image identification method according to claim 1, which is characterized in that the method also includes：
It obtains and modifies the modification instruction that the default similarity defines value；
Value is defined to the default similarity according to modification instruction to modify.
6. a kind of picture recognition device, which is characterized in that including：
Obtain module, the multiple pixels for including for obtaining picture to be identified and the picture to be identified in real time；
Characteristic point judgment module, for judging whether the pixel is special for each pixel in the multiple pixel
Sign point merges each feature vector extracted if the pixel is characterized the feature vector for a little extracting the pixel
To obtain fusion feature vector；
Similarity ratio value obtains module, by the fusion feature vector input training apparatus, wherein the training aids prestores original
Beginning picture fusion feature vector；Using the training aids by the fusion feature vector and the original image fusion feature vector
Identification is compared, obtains similarity ratio value；
Judgment module defines value for judging whether the similarity ratio value is less than default similarity, if similarity ratio
Example value is less than the default similarity and defines value, sends and determines that the picture to be identified is the prompt of fraud picture, extracts institute
State in fusion feature vector at least one unmatched feature vector of the original image fusion feature vector, will it is described at least
The corresponding pixel of one feature vector marks in the picture to be identified.
7. picture recognition device according to claim 6, which is characterized in that described device further includes second training module；
The second training module is used at least one described feature vector inputting the training aids；The training aids is carried out
Second training.
8. picture recognition device according to claim 7, which is characterized in that described device further includes modified module；
The modified module, which is used to obtain, modifies the modification instruction that the default similarity defines value, according to modification instruction pair
The default similarity defines value and modifies.
9. a kind of electronic equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor is realized described in any one of Claims 1 to 5 when executing the computer program
Image identification method.
10. a kind of computer readable storage medium, which is characterized in that the readable storage medium storing program for executing includes computer program, described
The requirement 1~5 of electronic equipment perform claim is described in any item computer program controls the readable storage medium storing program for executing when running where
Image identification method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810647364.7A CN108921209A (en) | 2018-06-21 | 2018-06-21 | Image identification method, device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810647364.7A CN108921209A (en) | 2018-06-21 | 2018-06-21 | Image identification method, device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108921209A true CN108921209A (en) | 2018-11-30 |
Family
ID=64420947
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810647364.7A Pending CN108921209A (en) | 2018-06-21 | 2018-06-21 | Image identification method, device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108921209A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109740336A (en) * | 2018-12-28 | 2019-05-10 | 北京云测信息技术有限公司 | Recognition methods, device and the electronic equipment of a kind of verification information in picture |
| CN110765304A (en) * | 2019-10-22 | 2020-02-07 | 珠海研果科技有限公司 | Image processing method, image processing device, electronic equipment and computer readable medium |
| CN110909188A (en) * | 2019-11-26 | 2020-03-24 | 上海秒针网络科技有限公司 | Method and device for determining inspection picture |
| CN111309817A (en) * | 2020-01-16 | 2020-06-19 | 秒针信息技术有限公司 | Behavior recognition method and device and electronic equipment |
| CN112906696A (en) * | 2021-05-06 | 2021-06-04 | 北京惠朗时代科技有限公司 | English image region identification method and device |
| CN114098536A (en) * | 2021-12-01 | 2022-03-01 | 湖南格兰博智能科技有限责任公司 | Obstacle crossing and trapped detection method for sweeping robot and sweeping robot |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101894260A (en) * | 2010-06-04 | 2010-11-24 | 北京化工大学 | Method for identifying forgery seal based on feature line randomly generated by matching feature points |
| CN104008379A (en) * | 2014-06-16 | 2014-08-27 | 河南科技大学 | Object recognition method based on surf |
| CN105426827A (en) * | 2015-11-09 | 2016-03-23 | 北京市商汤科技开发有限公司 | Living body verification method, device and system |
| CN105678232A (en) * | 2015-12-30 | 2016-06-15 | 中通服公众信息产业股份有限公司 | Face image feature extraction and comparison method based on deep learning |
| CN105868706A (en) * | 2016-03-28 | 2016-08-17 | 天津大学 | Method for identifying 3D model based on sparse coding |
| CN106203242A (en) * | 2015-05-07 | 2016-12-07 | 阿里巴巴集团控股有限公司 | A kind of similar image recognition methods and equipment |
| CN106250825A (en) * | 2016-07-22 | 2016-12-21 | 厚普（北京）生物信息技术有限公司 | A kind of at the medical insurance adaptive face identification system of applications fields scape |
| CN106778586A (en) * | 2016-12-08 | 2017-05-31 | 武汉理工大学 | Offline handwriting signature verification method and system |
| CN106815566A (en) * | 2016-12-29 | 2017-06-09 | 天津中科智能识别产业技术研究院有限公司 | A kind of face retrieval method based on multitask convolutional neural networks |
| CN106991451A (en) * | 2017-04-14 | 2017-07-28 | 武汉神目信息技术有限公司 | A kind of identifying system and method for certificate picture |
| CN107134048A (en) * | 2017-05-15 | 2017-09-05 | 广州市银科电子有限公司 | A kind of bill anti-counterfeit discrimination method of Intelligent Recognition watermark feature |
| CN107194376A (en) * | 2017-06-21 | 2017-09-22 | 北京市威富安防科技有限公司 | Mask fraud convolutional neural networks training method and human face in-vivo detection method |
| CN107221070A (en) * | 2017-05-24 | 2017-09-29 | 广州市银科电子有限公司 | A kind of bill anti-counterfeit discrimination method recognized based on master pattern fluorescent characteristics |
| CN107292287A (en) * | 2017-07-14 | 2017-10-24 | 深圳云天励飞技术有限公司 | Face identification method, device, electronic equipment and storage medium |
-
2018
- 2018-06-21 CN CN201810647364.7A patent/CN108921209A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101894260A (en) * | 2010-06-04 | 2010-11-24 | 北京化工大学 | Method for identifying forgery seal based on feature line randomly generated by matching feature points |
| CN104008379A (en) * | 2014-06-16 | 2014-08-27 | 河南科技大学 | Object recognition method based on surf |
| CN106203242A (en) * | 2015-05-07 | 2016-12-07 | 阿里巴巴集团控股有限公司 | A kind of similar image recognition methods and equipment |
| CN105426827A (en) * | 2015-11-09 | 2016-03-23 | 北京市商汤科技开发有限公司 | Living body verification method, device and system |
| CN105678232A (en) * | 2015-12-30 | 2016-06-15 | 中通服公众信息产业股份有限公司 | Face image feature extraction and comparison method based on deep learning |
| CN105868706A (en) * | 2016-03-28 | 2016-08-17 | 天津大学 | Method for identifying 3D model based on sparse coding |
| CN106250825A (en) * | 2016-07-22 | 2016-12-21 | 厚普（北京）生物信息技术有限公司 | A kind of at the medical insurance adaptive face identification system of applications fields scape |
| CN106778586A (en) * | 2016-12-08 | 2017-05-31 | 武汉理工大学 | Offline handwriting signature verification method and system |
| CN106815566A (en) * | 2016-12-29 | 2017-06-09 | 天津中科智能识别产业技术研究院有限公司 | A kind of face retrieval method based on multitask convolutional neural networks |
| CN106991451A (en) * | 2017-04-14 | 2017-07-28 | 武汉神目信息技术有限公司 | A kind of identifying system and method for certificate picture |
| CN107134048A (en) * | 2017-05-15 | 2017-09-05 | 广州市银科电子有限公司 | A kind of bill anti-counterfeit discrimination method of Intelligent Recognition watermark feature |
| CN107221070A (en) * | 2017-05-24 | 2017-09-29 | 广州市银科电子有限公司 | A kind of bill anti-counterfeit discrimination method recognized based on master pattern fluorescent characteristics |
| CN107194376A (en) * | 2017-06-21 | 2017-09-22 | 北京市威富安防科技有限公司 | Mask fraud convolutional neural networks training method and human face in-vivo detection method |
| CN107292287A (en) * | 2017-07-14 | 2017-10-24 | 深圳云天励飞技术有限公司 | Face identification method, device, electronic equipment and storage medium |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109740336A (en) * | 2018-12-28 | 2019-05-10 | 北京云测信息技术有限公司 | Recognition methods, device and the electronic equipment of a kind of verification information in picture |
| CN110765304A (en) * | 2019-10-22 | 2020-02-07 | 珠海研果科技有限公司 | Image processing method, image processing device, electronic equipment and computer readable medium |
| CN110909188A (en) * | 2019-11-26 | 2020-03-24 | 上海秒针网络科技有限公司 | Method and device for determining inspection picture |
| CN111309817A (en) * | 2020-01-16 | 2020-06-19 | 秒针信息技术有限公司 | Behavior recognition method and device and electronic equipment |
| CN111309817B (en) * | 2020-01-16 | 2023-11-03 | 秒针信息技术有限公司 | Behavior recognition method and device and electronic equipment |
| CN112906696A (en) * | 2021-05-06 | 2021-06-04 | 北京惠朗时代科技有限公司 | English image region identification method and device |
| CN114098536A (en) * | 2021-12-01 | 2022-03-01 | 湖南格兰博智能科技有限责任公司 | Obstacle crossing and trapped detection method for sweeping robot and sweeping robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108921209A (en) | Image identification method, device and electronic equipment | |
| US20190362193A1 (en) | Eyeglass positioning method, apparatus and storage medium | |
| CN109145766A (en) | Model training method, device, recognition methods, electronic equipment and storage medium | |
| CN109376631A (en) | A kind of winding detection method and device neural network based | |
| CN107194361A (en) | Two-dimentional pose detection method and device | |
| CN111898538B (en) | Certificate authentication method and device, electronic equipment and storage medium | |
| CN110082135A (en) | Equipment fault recognition methods, device and terminal device | |
| JP2021531571A (en) | Certificate image extraction method and terminal equipment | |
| CN111695609A (en) | Target damage degree determination method, target damage degree determination device, electronic device, and storage medium | |
| CN110472460A (en) | Face image processing process and device | |
| CN109522775A (en) | Face character detection method, device and electronic equipment | |
| CN110490839A (en) | The method, apparatus and computer equipment of failure area in a kind of detection highway | |
| CN108986125A (en) | Object edge extracting method, device and electronic equipment | |
| CN112052730B (en) | 3D dynamic portrait identification monitoring equipment and method | |
| CN107918767A (en) | Object detection method, device, electronic equipment and computer-readable medium | |
| CN108182457A (en) | For generating the method and apparatus of information | |
| CN105070094B (en) | A kind of parking stall measure system and method for detecting parking stalls based on machine vision | |
| CN112132812A (en) | Certificate checking method and device, electronic equipment and medium | |
| CN111126147B (en) | Image processing method, device and electronic system | |
| CN108960850A (en) | Method for anti-counterfeit and device, anti-fake traceability system | |
| CN111275070B (en) | Signature verification method and device based on local feature matching | |
| CN104376280B (en) | A kind of image code generation method towards Google glass | |
| CN112085721A (en) | Damage assessment method, device and equipment for flooded vehicle based on artificial intelligence and storage medium | |
| CN110458857A (en) | Central symmetry pel detection method, device, electronic equipment and readable storage medium storing program for executing | |
| CN114332809A (en) | Image identification method and device, electronic equipment and 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181130 |