CN108256530A - Image-recognizing method, device and equipment - Google Patents
Image-recognizing method, device and equipment Download PDFInfo
- Publication number
- CN108256530A CN108256530A CN201711482999.8A CN201711482999A CN108256530A CN 108256530 A CN108256530 A CN 108256530A CN 201711482999 A CN201711482999 A CN 201711482999A CN 108256530 A CN108256530 A CN 108256530A
- Authority
- CN
- China
- Prior art keywords
- image
- identified
- file
- edge line
- edge
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the present invention provides a kind of image-recognizing method, device and equipment, this method and includes：Edge detection is carried out to the image to be identified of file, the edge line of file in image to be identified is determined, judges the angle between arbitrary two edge lines of the file in the image to be identified whether in the range of predetermined angle, predetermined angle range includes：In 90 degree of default error is enclosed or in the default error range of 180 degree, if not, then determine that image to be identified is the image that shooting obtains, according to imaging characteristics, the type of effective district partial image is scanned copy or shooting gained, the workload artificially audited is reduced, improves recognition efficiency.
Description
Technical field
The present embodiments relate to a kind of field of computer technology more particularly to image-recognizing method, device and equipment.
Background technology
With the development of more and more network platforms, many businessmans are in order to market and the type of business of activating business
It needs to be registered in the network platform, publishing commodity information and advertisement information etc., in order to ensure the equity of user, the network platform needs
Businessman is distinguished and identified in the image of business license that platform uploads, the image of the business that ordinary circumstance uploads at least
Including photo or scan image, in the prior art, there is presently no the suitable schemes for distinguishing photo and scan image.
Invention content
The embodiment of the present invention provides a kind of image-recognizing method, device and equipment, and for solving, there is presently no suitable
The problem of scheme of differentiation photo and scan image.
First aspect of the embodiment of the present invention provides a kind of image-recognizing method, including：
Edge detection is carried out to the image to be identified of file, determines the edge line of file in image to be identified；
Judge the angle between arbitrary two edge lines of the file in the image to be identified whether in predetermined angle
In the range of；The predetermined angle range includes：In 90 degree of default error is enclosed or in the default error range of 180 degree；
If not, it is determined that the image to be identified is the image that shooting obtains.
In a kind of specific embodiment, the method further includes：
If so, determine the brightness change value of the intermediate region of the edge line of file in the image to be identified.
In a kind of specific embodiment, the method further includes：
If in the image to be identified in the edge line of file, there are the brightness change values of the intermediate region of an edge line
More than predetermined threshold value, it is determined that the image to be identified is the image that shooting obtains.
In a kind of specific embodiment, the method further includes：
If the brightness change value of the edge line of file is respectively less than the predetermined threshold value in the image to be identified, it is determined that
The image to be identified is the image that scanning obtains.
Second aspect of the embodiment of the present invention provides a kind of pattern recognition device, including：
First processing module carries out edge detection for the image to be identified to file, determines in image to be identified
The edge line of file；
Judgment module, for judging that the angle between arbitrary two edge lines of the file in the image to be identified is
It is no in the range of predetermined angle；The predetermined angle range includes：90 degree of default error encloses interior or 180 degree default mistake
In poor range；
Second processing module, if the judging result for the judgment module is no, it is determined that the image to be identified
To shoot obtained image.
Optionally, the Second processing module is additionally operable to：
If the judging result of the judgment module is yes, it is determined that in the image to be identified in the edge line of file
Between region brightness change value.
Optionally, described device further includes：
Third processing module, if in edge line for file in the image to be identified, there are in an edge line
Between the brightness change value in region be more than predetermined threshold value, it is determined that the image to be identified be to shoot obtained image.
Optionally, the third processing module is additionally operable to：
If the brightness change value of the edge line of file is respectively less than the predetermined threshold value in the image to be identified, it is determined that
The image to be identified is the image that scanning obtains.
The third aspect of the embodiment of the present invention provides a kind of server, including：Memory and processor；
The memory is used to store computer instruction；The processor by run memory storage it is described based on
The image-recognizing method described in first aspect any embodiment is realized in the instruction of calculation machine.
Fourth aspect of the embodiment of the present invention provides a kind of storage medium, including：Readable storage medium storing program for executing and computer instruction, institute
Computer instruction is stated to be stored in the readable storage medium storing program for executing；The computer instruction is used to implement any embodiment party of first aspect
Image-recognizing method described in formula.
The 5th aspect of the embodiment of the present invention provides a kind of program product, which (calculates including computer instruction
Machine program), which is stored in readable storage medium storing program for executing.Server or at least one processor of terminal can be from
Readable storage medium storing program for executing reads the computer instruction, and at least one processor performs the computer instruction and causes server or terminal
Implement aforementioned image-recognizing method.
Image-recognizing method provided in an embodiment of the present invention, device and equipment, according to the imaging characteristics of image in itself, to text
The image to be identified of part carries out edge detection, determines the edge line of file in image to be identified, judges described to be identified
Angle between arbitrary two edge lines of file in image whether in 90 degree of default error is enclosed or 180 degree it is pre-
If in error range, if not, it is determined that image to be identified is the image that shooting obtains, and the type of effective district partial image is scanning
Part or shooting gained, reduce the workload artificially audited, improve recognition efficiency.
Description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Some bright embodiments, for those of ordinary skill in the art, without having to pay creative labor, can be with
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the flow chart of image-recognizing method embodiment one provided in an embodiment of the present invention；
Fig. 2 is the flow chart of image-recognizing method embodiment two provided in an embodiment of the present invention；
Fig. 3 is the flow chart of image-recognizing method embodiment three provided in an embodiment of the present invention；
Fig. 4 is the flow chart of image-recognizing method example IV provided in an embodiment of the present invention；
Fig. 5 is the structure diagram of pattern recognition device embodiment one provided in an embodiment of the present invention；
Fig. 6 is the structure diagram of pattern recognition device embodiment two provided in an embodiment of the present invention；
Fig. 7 is the structure diagram of server example two provided in an embodiment of the present invention.
Specific embodiment
Purpose, technical scheme and advantage to make the embodiment of the present invention are clearer, below in conjunction with the embodiment of the present invention
In attached drawing, the technical solution in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
Part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
The all other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Fig. 1 is the flow chart of image-recognizing method embodiment one provided in an embodiment of the present invention, as shown in Figure 1, the image
Recognition methods can be applicable to server, in the terminal devices such as mobile phone, personal computer, laptop, the image-recognizing method
Specifically include following steps：
S101：Edge detection is carried out to the image to be identified of file, determines the edge line of file in image to be identified.
In this step, in order to determine image to be identified be shooting gained or scanning gained, it is necessary first to this is treated
The image of identification carries out edge detection, the edge line of the file in image is obtained, so that the situation subsequently according to edge line determines
The type of image, this document can be common paper document or certificate, such as the identity card of user, passport, enterprise
Business license, safety monitoring file etc., this this programme is not limited.
In this scenario, the purpose of edge detection is the apparent point of brightness change in reference numbers image, in image attributes
Significant changes usually reflect the critical event and variation of attribute, Image Edge-Detection significantly reduces data volume, and
And it eliminates it is considered that incoherent information, remains the important structure attribute of image, such as the straight line at the edge in image.
The method of common edge detection is included based on the one kind searched one kind and passed through based on zero.Method based on lookup passes through searching
Maximum and minimum value in image first derivative detects boundary, typically by boundary alignment in the direction of gradient maximum.It is based on
Zero method passed through passes through to find boundary, typically Laplacian zero crossings or non-by finding image second order derivative zero
The zero crossing that linear differential represents.
Specifically, the edge detection method based on search calculates edge strength first, usually represented with first derivative, such as
Then gradient-norm estimates the local direction at edge, the direction of generally use gradient with calculating, and finds local ladder using this direction
Spend the maximum value of mould.Method based on zero crossing finds the zero cross point of the second dervative obtained by image to position edge, leads to
The zero cross point of common Laplace operator or nonlinear differential equation.For the detection method we specifically used in the program
Case is not limited.
S102：Judge the angle between arbitrary two edge lines of the file in image to be identified whether in predetermined angle
In the range of；Predetermined angle range includes：In 90 degree of default error is enclosed or in the default error range of 180 degree.
In this step, if the image to be identified of file is shot for user, by the angle of shooting and user institute
The factors such as position influence, can not be under normal circumstances the plane for being exactly perpendicularly to file shooting angle, therefore this
The shooting of sample visually cause the file after imaging be not in the picture each angle be 90 degree right angle situation, and sweep
Tracing is not in the problem as this, and this programme provides a kind of side for judging image to be identified and whether shooting gained accordingly
Case, the angular error of the file in multiple measurement or experience setting scan image figure, such as once, it is meant that scanning
Image in the angle of corner of file may be 89 to 91 range once, accordingly, a predetermined angle range is set, according to
Whether the angle between any two edge line of the file in the image to be identified that aforementioned edge detection obtains is pre- at this
If within angular range.
In the program, the angle between the adjacent edge line of the file in image to be identified should be 90 degree or so,
Angle between non-conterminous edge line should be in 180 degree or so, therefore predetermined angle range may be configured as including：90 degree pre-
In if error is enclosed or in the default error range of 180 degree.Its meaning refers to allow have certain error model about 90 degree
It encloses or allows have certain error range above and below 180 degree.
S103：If not, it is determined that image to be identified is the image that shooting obtains.
In this step, if it is determined that go out in the edge line that file is detected in image to be identified, arbitrary two
When angle between edge line is not within pre-set angular range, it may be determined that the corner of the file in the image with it is straight
Angle difference is bigger, and when being scanned to file, then be not in such case, therefore can determine the image to be identified
To shoot obtained image.
Image-recognizing method provided in this embodiment by carrying out edge detection to the file in image to be identified, obtains
To the edge line of this document, then to judging the angle between edge line whether in preset angular range, so that it is determined that should
What whether image to be identified shot, according to imaging characteristics, the type of effective district partial image is scanned copy or shooting
Gained reduces the workload artificially audited, and improves recognition efficiency.
Fig. 2 is the flow chart of image-recognizing method embodiment two provided in an embodiment of the present invention, as shown in Fig. 2, above-mentioned
On the basis of embodiment one, the image-recognizing method is further comprising the steps of：
S104：If so, determine the brightness change value of the intermediate region of the edge line of file in image to be identified.
In this step, if server or equipment define arbitrary two edge lines in image to be identified
Angle can then determine the image to be identified as scanning gained, but there is also the non-of shooting in the range of predetermined angle
Normal accurate situation, therefore for the accuracy for further improving image identification, can continue to the image to be identified
Edge line carry out brightness detection, the brightness change value of identification edge line intermediate region.
It is different for the brightness change value of the edge line of different files, thus can set different brightness change values into
The different image identification of row, is not limited this this programme.
Below with the file is for business license, image type is identified to the brightness change value for using edge line
Scheme illustrates, then the method further includes：
S105：If in image to be identified in the edge line of file, there are the brightness changes of the intermediate region of an edge line
Value is more than predetermined threshold value, it is determined that image to be identified is the image that shooting obtains.
In this step, since user is to business license, when files are taken pictures, edges edge can inevitably be clapped
To other object, color is more big changes, and the edge color of scanned copy varies less, simultaneously because business license rectangle
There is word in edge corner, then selects the intermediate region calculating brightness change at edge, and brightness change belongs to greatly what is taken pictures, and brightness change is very
Small is scanned copy.Therefore threshold value can be set to judge the brightness change of edge line, the file in image to be identified
The brightness change value of edge line intermediate region when being more than threshold value, it is determined that image to be identified be to shoot obtained image.
Image-recognizing method provided in this embodiment by carrying out edge detection to the file in image to be identified, obtains
To the edge line of this document, then to judging the angle between edge line whether in preset angular range, so that it is determined that should
What whether image to be identified shot, and combined according to the brightness of edge line according to imaging characteristics, effective district partial image
Type be shooting gained, reduce the workload artificially audited, improve recognition efficiency.
Fig. 3 is the flow chart of image-recognizing method embodiment three provided in an embodiment of the present invention, as shown in figure 3, above-mentioned
On the basis of embodiment two, which further includes：
S106：If the brightness change value of the edge line of file is respectively less than predetermined threshold value in image to be identified, it is determined that treats
The image of identification is the image that scanning obtains.
In this step, it is similar with above-described embodiment two, since user takes pictures to files such as business licenses
When, edges edge can inevitably photograph other object, and color is more big changes, and the variation of the edge color of scanned copy is very
Small, simultaneously because there is word in business license rectangular edge corner, then selects the intermediate region calculating brightness change at edge, brightness becomes
Change belongs to what is taken pictures greatly, and brightness change very little is scanned copy.Therefore threshold value can be set to sentence the brightness change of edge line
It is disconnected, when the brightness change value of the edge line intermediate region of the file in image to be identified is less than threshold value, it is determined that be identified
Image be the obtained image of scanning.
Image-recognizing method provided in this embodiment by carrying out edge detection to the file in image to be identified, obtains
To the edge line of this document, then to judging the angle between edge line whether in preset angular range, so that it is determined that should
What whether image to be identified shot, and combined according to the brightness of edge line according to imaging characteristics, effective district partial image
Type be scanned copy, reduce the workload artificially audited, improve recognition efficiency.
Fig. 4 is the flow chart of image-recognizing method example IV provided in an embodiment of the present invention, as shown in figure 4, above-mentioned
On the basis of any embodiment, below by taking the image of business license as an example, the image-recognizing method provided this programme is lifted
Example explanation.
According to scanned copy and the business license imaging characteristics taken pictures, the rectangle grid ratio in the scan image of business license
Image obtained by taking pictures is more neat, and rectangular edge is in horizontal and vertical shape.When in addition taking pictures to business license, edges
Edge can inevitably photograph other object, and color is more big changes, and the edge color of scanned copy varies less.According to this two
Point is differentiated, main technical schemes are as follows：
1) edge detection (such as canny), is carried out to acquiring the image come first, edge inside image is found according to gradient.So
The straight line of image is found according to hough transformation afterwards, the straight line detected is divided into close to horizontal and subvertical, respectively to water
Gentle vertical straight line straight line cluster finds the rectangular edge line of business license.
2), since there is word in business license rectangular edge corner, then the intermediate region calculating brightness change at edge is selected, it is bright
Degree variation belongs to what is taken pictures greatly, and brightness change very little is scanned copy.
Based on above-mentioned principle, the specific implementation step of the program is：
S201：Input image to be identified.
S202：Edge detection is carried out to image to be identified.
S203：The straight line that edge detection obtains is detected (angle between detection of straight lines).
S204：Straight line of the statistics more than 179 degree and less than 1 degree and more than 89 degree and less than 91 degree is clustered.
S205：The straight line for judging to meet above-mentioned condition whether there is.If so then execute S206, if otherwise performing S209.
S206：Count the brightness change value at edge.
S207：Judge brightness change value whether in threshold range.If so then execute S208, if otherwise performing S209.
S208：It is scanned copy to determine image.
S209：Determine image for shooting image.
The image-recognizing method provided in examples detailed above, for business license upload image file, according to it is respective into
As feature distinguishes.Effective district divides the scanned copy of business license and takes pictures, and reduces the workload of auditor.
Fig. 5 is the structure diagram of pattern recognition device embodiment one provided in an embodiment of the present invention, as shown in figure 5, should
Pattern recognition device 10 includes：
First processing module 11 carries out edge detection for the image to be identified to file, determines image to be identified
The edge line of middle file；
Judgment module 12, for judging the angle between arbitrary two edge lines of the file in the image to be identified
Whether in the range of predetermined angle；The predetermined angle range includes：90 degree of default error is enclosed interior or 180 degree default
In error range；
Second processing module 13, if the judging result for the judgment module is no, it is determined that the figure to be identified
As the image obtained for shooting.
Optionally, the Second processing module 13 is additionally operable to：
If the judging result of the judgment module is yes, it is determined that in the image to be identified in the edge line of file
Between region brightness change value.
The pattern recognition device of text message provided in this embodiment, for performing the technical side in preceding method embodiment
Case, implementing principle and technical effect are similar, and details are not described herein.
Fig. 6 is the structure diagram of pattern recognition device embodiment two provided in an embodiment of the present invention, as shown in fig. 6,
On the basis of above-described embodiment one, the file is business license, and described image identification device 10 further includes：
Third processing module 14, if in edge line for file in the image to be identified, there are an edge lines
The brightness change value of intermediate region is more than predetermined threshold value, it is determined that the image to be identified is the image that shooting obtains.
Optionally, the third processing module 14 is additionally operable to：
If the brightness change value of the edge line of file is respectively less than the predetermined threshold value in the image to be identified, it is determined that
The image to be identified is the image that scanning obtains.
Pattern recognition device provided in this embodiment for performing the technical solution in preceding method embodiment, is realized
Principle is similar with technique effect, and details are not described herein.
Fig. 7 is the structure diagram of server example two provided in an embodiment of the present invention, as shown in fig. 7, the server
20 include：Memory 21 and processor 22；
The memory 21 is used to store computer instruction；The processor 22 is used to run the institute of the memory storage
Computer instruction is stated, the computer instruction realizes the image-recognizing method that aforementioned embodiments provide.
It should be understood that the program is in addition to that can be realized in the server, it can also be in computer, mobile phone, intelligent terminal, calculating
It is realized in the other-ends equipment such as machine, this this programme is not limited.
The embodiment of the present invention also provides a kind of storage medium, including：Readable storage medium storing program for executing and computer instruction, the calculating
Machine instruction is stored in the readable storage medium storing program for executing；The image that the computer instruction is used to implement aforementioned embodiments offer is known
Other method.
The embodiment of the present invention also provides a kind of program product, which includes computer instruction (i.e. computer journey
Sequence), which is stored in readable storage medium storing program for executing.Server or at least one processor of terminal can be from readable
Storage medium reads the computer instruction, and at least one processor performs the computer instruction and server or terminal are implemented
Aforementioned image-recognizing method.
In above-mentioned server in the specific implementation, it should be understood that processor can be central processing unit (English：Central
Processing Unit, referred to as：CPU), it can also be other general processors, digital signal processor (English：Digital
Signal Processor, referred to as：DSP), application-specific integrated circuit (English：Application Specific Integrated
Circuit, referred to as：ASIC) etc..General processor can be microprocessor or the processor can also be any conventional place
Manage device etc..The step of method with reference to disclosed in the embodiment of the present invention can be embodied directly in hardware processor perform completion or
Hardware and software module combination in person's processor perform completion.
One of ordinary skill in the art will appreciate that：Realizing all or part of step of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Aforementioned program can be stored in a computer read/write memory medium.The journey
Sequence when being executed, performs the step of including above-mentioned each method embodiment；And aforementioned storage medium includes：Read-only memory (English
Text：Read-only memory, abbreviation：ROM), RAM, flash memory, hard disk, solid state disk, tape (English：magnetic
Tape), floppy disk (English：Floppy disk), CD (English：Optical disc) and its arbitrary combination.
Finally it should be noted that：The above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe is described in detail the present invention with reference to foregoing embodiments, it will be understood by those of ordinary skill in the art that：Its according to
Can so modify to the technical solution recorded in foregoing embodiments either to which part or all technical features into
Row equivalent replacement；And these modifications or replacement, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (10)
1. a kind of image-recognizing method, which is characterized in that including：
Edge detection is carried out to the image to be identified of file, determines the edge line of file in image to be identified；
Judge the angle between arbitrary two edge lines of the file in the image to be identified whether in predetermined angle range
It is interior；The predetermined angle range includes：In 90 degree of default error is enclosed or in the default error range of 180 degree；
If not, it is determined that the image to be identified is the image that shooting obtains.
2. according to the method described in claim 1, it is characterized in that, the method further includes：
If so, determine the brightness change value of the intermediate region of the edge line of file in the image to be identified.
3. according to the method described in claim 2, it is characterized in that, the method further includes：
If in the image to be identified in the edge line of file, the brightness change value there are the intermediate region of an edge line is more than
Predetermined threshold value, it is determined that the image to be identified is the image that shooting obtains.
4. according to the method described in claim 3, it is characterized in that, the method further includes：
If the brightness change value of the edge line of file is respectively less than the predetermined threshold value in the image to be identified, it is determined that described
Image to be identified is the image that scanning obtains.
5. a kind of pattern recognition device, which is characterized in that including：
First processing module carries out edge detection for the image to be identified to file, determines file in image to be identified
Edge line；
Judgment module, for judge the angle between arbitrary two edge lines of the file in the image to be identified whether
In the range of predetermined angle；The predetermined angle range includes：90 degree of default error encloses interior or 180 degree default error model
In enclosing；
Second processing module, if the judging result for the judgment module is no, it is determined that the image to be identified is claps
The image taken the photograph.
6. device according to claim 5, which is characterized in that the Second processing module is additionally operable to：
If the judging result of the judgment module is yes, it is determined that the middle area of the edge line of file in the image to be identified
The brightness change value in domain.
7. device according to claim 6, which is characterized in that described device further includes：
Third processing module, if in edge line for file in the image to be identified, there are the middle areas of an edge line
The brightness change value in domain is more than predetermined threshold value, it is determined that the image to be identified is the image that shooting obtains.
8. device according to claim 7, which is characterized in that the third processing module is additionally operable to：
If the brightness change value of the edge line of file is respectively less than the predetermined threshold value in the image to be identified, it is determined that described
Image to be identified is the image that scanning obtains.
9. a kind of server, which is characterized in that including：Memory and processor；
The memory is used to store computer instruction；The processor is used to run the computer of the memory storage
Claims 1-4 any one of them image-recognizing method is realized in instruction.
10. a kind of storage medium, which is characterized in that including：Readable storage medium storing program for executing and computer instruction, the computer instruction are deposited
Storage is in the readable storage medium storing program for executing；The computer instruction is used to implement the identification of Claims 1-4 any one of them image
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711482999.8A CN108256530B (en) | 2017-12-29 | 2017-12-29 | Image recognition method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711482999.8A CN108256530B (en) | 2017-12-29 | 2017-12-29 | Image recognition method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108256530A true CN108256530A (en) | 2018-07-06 |
| CN108256530B CN108256530B (en) | 2021-12-07 |
Family
ID=62725327
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711482999.8A Active CN108256530B (en) | 2017-12-29 | 2017-12-29 | Image recognition method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108256530B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021031523A1 (en) * | 2019-08-21 | 2021-02-25 | 创新先进技术有限公司 | Document recognition method and device |
| CN114693629A (en) * | 2022-03-25 | 2022-07-01 | 北京城市网邻信息技术有限公司 | Image recognition method and device, electronic equipment and readable medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5901253A (en) * | 1996-04-04 | 1999-05-04 | Hewlett-Packard Company | Image processing system with image cropping and skew correction |
| CN106203431A (en) * | 2016-07-14 | 2016-12-07 | 国芯科技（北京）有限公司 | A kind of image-recognizing method and device |
| CN106846011A (en) * | 2016-12-30 | 2017-06-13 | 金蝶软件（中国）有限公司 | Business license recognition methods and device |
| CN106886776A (en) * | 2017-02-23 | 2017-06-23 | 山东浪潮云服务信息科技有限公司 | The application model of license electronization is realized in a kind of utilization image recognition |
| CN107463875A (en) * | 2017-07-03 | 2017-12-12 | 金讯***管理有限公司 | A kind of method and apparatus for judging personnel identity |
-
2017
- 2017-12-29 CN CN201711482999.8A patent/CN108256530B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5901253A (en) * | 1996-04-04 | 1999-05-04 | Hewlett-Packard Company | Image processing system with image cropping and skew correction |
| CN106203431A (en) * | 2016-07-14 | 2016-12-07 | 国芯科技（北京）有限公司 | A kind of image-recognizing method and device |
| CN106846011A (en) * | 2016-12-30 | 2017-06-13 | 金蝶软件（中国）有限公司 | Business license recognition methods and device |
| CN106886776A (en) * | 2017-02-23 | 2017-06-23 | 山东浪潮云服务信息科技有限公司 | The application model of license electronization is realized in a kind of utilization image recognition |
| CN107463875A (en) * | 2017-07-03 | 2017-12-12 | 金讯***管理有限公司 | A kind of method and apparatus for judging personnel identity |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021031523A1 (en) * | 2019-08-21 | 2021-02-25 | 创新先进技术有限公司 | Document recognition method and device |
| CN114693629A (en) * | 2022-03-25 | 2022-07-01 | 北京城市网邻信息技术有限公司 | Image recognition method and device, electronic equipment and readable medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108256530B (en) | 2021-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2017302250B2 (en) | Optical character recognition in structured documents | |
| US10360689B2 (en) | Detecting specified image identifiers on objects | |
| WO2017162069A1 (en) | Image text identification method and apparatus | |
| CA2867365C (en) | Method, system and computer storage medium for face detection | |
| CN109190539A (en) | Face identification method and device | |
| US11682225B2 (en) | Image processing to detect a rectangular object | |
| CN110913243B (en) | Video auditing method, device and equipment | |
| JP2014057306A (en) | Document image binarization and segmentation using image phase congruency | |
| US20150287168A1 (en) | Duplicate check image resolution | |
| US9373053B2 (en) | Image processor with edge selection functionality | |
| WO2019019595A1 (en) | Image matching method, electronic device method, apparatus, electronic device and medium | |
| CN107368829B (en) | Method and apparatus for determining rectangular target area in input image | |
| CN105354571B (en) | Distortion text image baseline estimation method based on curve projection | |
| CN111160395A (en) | Image recognition method and device, electronic equipment and storage medium | |
| US20150003681A1 (en) | Image processing apparatus and image processing method | |
| Zhao et al. | Automatic blur region segmentation approach using image matting | |
| CN108256530A (en) | Image-recognizing method, device and equipment | |
| CN110135288B (en) | Method and device for quickly checking electronic certificate | |
| CN110929738A (en) | Certificate card edge detection method, device, equipment and readable storage medium | |
| Shi et al. | Segment-based adaptive window and multi-feature fusion for stereo matching | |
| CN113762220A (en) | Object recognition method, electronic device, and computer-readable storage medium | |
| CN109033797B (en) | Permission setting method and device | |
| CN111768345A (en) | Method, device and equipment for correcting back image of identity card and storage medium | |
| Zhao et al. | Using region-based saliency for 3d interest points detection | |
| CN110880023A (en) | Method and device for detecting certificate picture |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |