CN105787419A - Palm detection method and palm detection system for palm image - Google Patents
Palm detection method and palm detection system for palm image Download PDFInfo
- Publication number
- CN105787419A CN105787419A CN201410816108.8A CN201410816108A CN105787419A CN 105787419 A CN105787419 A CN 105787419A CN 201410816108 A CN201410816108 A CN 201410816108A CN 105787419 A CN105787419 A CN 105787419A
- Authority
- CN
- China
- Prior art keywords
- palm
- image
- hog
- unit
- palm image
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a palm detection method for a palm image of a computer system. The method comprises the steps of graying a palm image by a trigger command system; extracting the features of a gradient orientation histogram (HOG) of the above grayed palm image; and classifying the features of the HOG of a target palm image by means of a trained support vector machine (SVM) classifier. The trained SVM classifier is obtained in advance based on the classified training process of images containing valid palm patterns and images containing invalid palm patterns. Based on the above method, palm patterns in palm images can be effectively detected.
Description
Technical field
The application relates to the picture recognition field in calculating field, particularly relates to palm detection method and the system of a kind of palm image.
Background technology
Personal recognition security fields are becoming increasingly popular, for instance depositor in the authentication of bank, the gate control system of domestic, and in company attendance checking system to employee, all can use Palm Print Recognition System.
Personal recognition is when performing palmmprint, it will usually first absorb the picture of the palm of a user, then extracts the palmmprint of palm in picture and mates with the palmmprint prestored in system, as the match is successful, then it is assumed that personal recognition success, user identity is legal.Otherwise, then the operation requests of user is refused.
Absorb the picture of palm of user in Palm Print Recognition System after, system generally first needs whether contain effective palm figure in the picture judging to absorb, in order to carry out the operation that follow-up palmmprint extracts.If being absent from effective palm figure in picture, then follow-up operation cannot be carried out.Prior art is usually by the position of specific hardware facility constraints palm, for instance the palm model of an indent or corresponding baffle plate, and to guarantee that the palm of user is when being taken picture, it is positioned at correct position.This type of Palm Print Recognition System, in view of its requirement to hardware, user carries out the operation of personal recognition, is unfavorable for the popularization of Palm Print Recognition System after cannot utilizing common camera shooting palm at any time.And user is when using Palm Print Recognition System, and because its palm is limited in certain scope, Consumer's Experience is also poor.
Therefore, the present invention will provide for a kind of method of new palm detection, to overcome the problems referred to above.
Summary of the invention
The embodiment of the present application provides the detection system and method for a kind of palm image, it is possible to whether contain palm figure in detection palm image.
For solving the problems referred to above, the embodiment of the present application provides a kind of method and system building intelligent rules model.
A kind of palm detection method of the palm image of computer system, including:
According to triggering command system by palm image gray processing;
Extract the HOG feature of the palm image of above-mentioned gray processing;
The HOG feature to target palm image of trained SVM classifier is classified;
Wherein, described SVM classifier is that the image beforehand through the image containing effective palm figure with containing invalid palm figure carries out classification based training and obtains.
A kind of palm detection system of palm image, including:
Gray shade unit, for by palm image gray processing;
HOG feature extraction unit, for being extracted its HOG feature from above-mentioned by the palm image after gray processing;
SVM classifier taxon, for calculating in the HOG feature of palm image whether have effective palm figure;
Output unit, for exporting the classification results of above-mentioned SVM classifier.
The technical scheme provided from above the embodiment of the present application, in the embodiment of the present application, the figure of the palm of palm image can effectively be detected.
Accompanying drawing explanation
Accompanying drawing described herein is used for providing further understanding of the present application, constitutes the part of the application, and the schematic description and description of the application is used for explaining the application, is not intended that the improper restriction to the application.In the accompanying drawings:
Fig. 1 is the simple process schematic diagram of the Palm Print Recognition System of this prior art;
The flow chart that Fig. 2 provides for the embodiment of the present application;
The system construction drawing that Fig. 3 provides for the embodiment of the present application;
Detailed description of the invention
For making the purpose of the application, technical scheme and advantage clearly, below in conjunction with the application specific embodiment and corresponding accompanying drawing, technical scheme is clearly and completely described.Obviously, described embodiment is only some embodiments of the present application, rather than whole embodiments.Based on the embodiment in the application, the every other embodiment that those of ordinary skill in the art obtain under not making creative work premise, broadly fall into the scope of the application protection.
As it is shown in figure 1, be the simple flow chart of a kind of Palm Print Recognition System, during its work, Palm Print Recognition System first carries out the collection of palm image, i.e. Palm Print Recognition System is by the picture of the palm of photographic head shooting user;Then, acquired picture is carried out palm detection by Palm Print Recognition System, namely, whether the picture that Palm Print Recognition System detection is acquired also has effective palm figure, so-called effective palm figure refers to and Palm Print Recognition System can be made to extract palmmprint in this palm figure, and can accurately judge to judge that whether this palmmprint is legal;If testing result is for having palm figure effectively, then the palmmprint of the palm in picture and the palmmprint being pre-stored in Palm Print Recognition System can be compared by Palm Print Recognition System;Last Palm Print Recognition System output comparison result, and terminate the work of this personal recognition;As Palm Print Recognition System is not detected by effective palm figure in the step that palm detects, then Palm Print Recognition System directly exports the result of recognition failures, and terminates the work of this personal recognition.
By the above-mentioned workflow to Palm Print Recognition System it can be seen that palm detects the importance in Palm Print Recognition System.The palm detection method of the palm image of the application is HOG (HistogramofGradient) feature by extracting palm image, and by SVM (SupportVectorMachine) grader training result to effective palm image and invalid palm image, it is judged that whether target palm image contains effective palm figure.The HOG feature of image can describe the edge shape of figure in image, and palm generally comprises a palmar aspect and coupled five fingers, belongs to the figure that comparison is unique, therefore, the HOG feature of palm image can effectively describe the shape of palm.When training SVM classifier, positive sample label and negative sample label can be given respectively by the HOG feature of the HOG feature of the positive sample of palm image containing effective palm figure and the palm image negative sample not containing effective palm figure, and be entered in SVM classifier and be trained, difference according to the positive sample identification inputted and the HOG feature of negative sample mark, SVM classifier obtains the classifying face of a HOG feature, the side of this classifying face is the HOG feature of the palm image containing effective palm figure, the opposite side of classifying face is the HOG feature of the palm image not containing effective palm figure.So, when the HOG feature needing estimative target palm image is imported into SVM classifier, SVM classifier goes out the position relationship of itself and classifying face according to its HOG feature calculation, such as, the HOG feature of target palm image is positioned at the side containing effective palm image of classifying face, then this target palm image will be determined it and contains effective palm figure, then Palm Print Recognition System carries out follow-up personal recognition work according to this judged result, if the HOG feature of this target palm image falls into the side not containing effective palm image of classifying face, then Palm Print Recognition System directly exports the result of recognition failures according to this judged result.
By the way, it would be desirable to the HOG feature of estimative target palm image is input to trained SVM classifier, it is possible to determine in this target palm image whether contain effective palm figure.Wherein, include complete palm image in order to train the palm image of the positive sample of SVM classifier to be or enough carry out the image of most of palm area of personal recognition, and the palm in this palm image can carry out left-right rotation with wrist for fulcrum, what rotate ranges preferably from 90 degree, left and right, naturally it is also possible to beyond 90 degree.And in order to train the palm image of the negative sample of SVM classifier to include not contain the image that direction deviation that the image of palm figure, palm rotate is bigger, for instance more than 90 degree, and contain only small part and be not enough to carry out the image of the palm area of personal recognition.
By the palm detection mode of above-mentioned palm image, substantially can carry out in the condition not receiving restriction when the palm image of user is collected, so can improve the experience of user.
As in figure 2 it is shown, be the embodiment of the palm detection method of the palm image of the application, its specific works step is as follows:
S101: system accepts triggering command.
System accepts triggering command, prepares target image is carried out palm detection.
S102: system is by target palm image gray processing.
For extracting the shade of gray information of target palm image, i.e. the HOG feature of palm image, target palm image first can be carried out gray processing process by system.
S103: system extracts the HOG feature of target palm image.
System, after obtaining the palm image after gray processing processes, extracts its HOG feature.For improving the calculating speed of system, target palm image can be compressed by system.Such as by target palm image normalization, namely it is compressed into the image of 64*64 pixel size.The HOG feature of the target palm image after system extraction gray processing can be undertaken by following a kind of embodiment, such as, after target palm image normalization after gray processing is become the image of 64*64 pixel size, target palm image is split with 8*8 pixel for a unit, and every 2*2=4 unit constitutes a region, and carry out to partly overlap between region, in this embodiment, the degree of overlapping in region is 0.5, namely, in the region that each two is adjacent, 2 adjacent unit are had to be shared by the region that above-mentioned two is adjacent.By above-mentioned partitioning scheme, the target palm image of each 64*64 pixel just includes 8*8=64 unit, and 64 unit constitute 7*7=49 the region that degree of overlapping is 0.5 altogether.In the present embodiment, the HOG of target palm image is characterized by adding up in histogrammic mode, concrete, first extracts the HOG feature of each pixel, i.e. the shade of gray feature of each pixel.Then all projecting on 9 vectors by the HOG feature of 8*8 pixel of each unit, wherein above-mentioned 9 vectors are spent the vector of 9 deciles being divided into by 0 degree-180 and are obtained.So, each unit includes the HOG characteristic vector of one 9 dimension.And each region includes 4 unit, after all HOG characteristic vectors in each region are linked up, each region just includes the HOG characteristic vector of a 4*9=36 dimension, it can thus be appreciated that, the characteristic vector in all regions constitutes the HOG characteristic vector of target palm image after linking up, that is, the HOG characteristic vector that the characteristic vector of every target image being compressed into 64*64 pixel is a 36*7*7=1764 dimension.By the way, system can extract the HOG characteristic vector of target palm image.Certainly, in other embodiments, target palm compression of images can also be become the picture of 64*124 pixel or other pixels by system, such as when being compressed into 64*124 pixel, still target image is divided into the unit being made up of 2*2 pixel, the region being made up of 2*2 unit, the degree of overlapping in region remains 0.5, and also be by the HOG Projection Character of each unit to the vector of 9 deciles, so, it is compressed into after all HOG characteristic vectors of the target image of 64*124 link up just to include the HOG characteristic vector of a 2*2*9*7*15=3780 dimension.Additionally, when region is with the degree of overlapping overlap of 0.5, the shade of gray information that can extract the target each pixel of palm image is repeatedly extracted, thus obtaining the more shade of gray information of target palm image, it is possible to make the HOG feature extracted better describe the figure of palm of target palm image.System can extract the HOG feature of target palm image by the way, thus knowing the information of the edge shape of palm in image.
S104: the HOG feature to target palm image of trained SVM classifier is classified.
SVM classifier is after by the palm image of positive sample and the palm image training of negative sample, obtain a HOG tagsort face distinguishing positive sample and negative sample, when the HOG feature of target palm image is imported into after the SVM classifier being trained to, SVM classifier goes out the position relationship of itself and classifying face according to the HOG feature calculation of this target palm image, namely the HOG feature calculating target palm image is positioned at the classification of positive sample, is also in the classification of negative sample.
S105: the HOG feature of the target palm image that system calculates according to SVM classifier is relative to classification relation of plane, it is judged that whether this target palm image contains effective palm figure.
The HOG feature of the target palm image calculated according to SVM classifier is relative to classification relation of plane, if the HOG feature that target palm image is positioned at is in the side of the positive sample class of classifying face, then by system, this target palm image will be judged that it contains effective palm figure, Palm Print Recognition System according to this result of determination, will carry out follow-up personal recognition work.If the HOG feature of this target palm image is positioned at the side of the negative sample classification of classifying face, then Palm Print Recognition System can judge that this target palm image does not contain effective palm figure, and Palm Print Recognition System can directly export the result that personal recognition is failed.
By said process, Palm Print Recognition System may determine that whether contain effective palm image in target palm image, it is possible to makes system determine the need for carrying out the follow-up work of personal recognition according to above-mentioned judged result.
A kind of embodiment of the palm detection system of the palm image of the application introduced below
Receiving unit 201, is used for accepting triggering command;
Gray shade unit 202, for by target palm image gray processing;
HOG feature extraction unit 203, for from extracting its HOG feature in the target palm image after gray processing;
SVM classifier taxon 204, for calculating in the HOG feature of target palm image whether have effective palm figure.
SVM classifier is after the palm image of positive sample and the palm image training of negative sample, one obtained distinguishes the classifying face of the HOG feature of above-mentioned positive sample and negative sample, the position relationship of the HOG feature of the classifying face according to SVM classifier and target palm image, it is determined that whether target palm image has effective palm figure.
Output unit 205, for being exported by the classification results of above-mentioned SVM classifier, and the system that passes to carries out follow-up work.
Those skilled in the art are it should be appreciated that embodiments of the invention can be provided as method, system or computer program.Therefore, the present invention can adopt the form of complete hardware embodiment, complete software implementation or the embodiment in conjunction with software and hardware aspect.And, the present invention can adopt the form at one or more upper computer programs implemented of computer-usable storage medium (including but not limited to disk memory, CD-ROM, optical memory etc.) wherein including computer usable program code.
The present invention is that flow chart and/or block diagram with reference to method according to embodiments of the present invention, equipment (system) and computer program describe.It should be understood that can by the combination of the flow process in each flow process in computer program instructions flowchart and/or block diagram and/or square frame and flow chart and/or block diagram and/or square frame.These computer program instructions can be provided to produce a machine to the processor of general purpose computer, special-purpose computer, Embedded Processor or other programmable data processing device so that the instruction performed by the processor of computer or other programmable data processing device is produced for realizing the device of function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions may be alternatively stored in and can guide in the computer-readable memory that computer or other programmable data processing device work in a specific way, the instruction making to be stored in this computer-readable memory produces to include the manufacture of command device, and this command device realizes the function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions also can be loaded in computer or other programmable data processing device, make on computer or other programmable devices, to perform sequence of operations step to produce computer implemented process, thus the instruction performed on computer or other programmable devices provides for realizing the step of function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame.
In a typical configuration, computing equipment includes one or more processor (CPU), input/output interface, network interface and internal memory.
Internal memory potentially includes the forms such as the volatile memory in computer-readable medium, random access memory (RAM) and/or Nonvolatile memory, such as read only memory (ROM) or flash memory (flashRAM).Internal memory is the example of computer-readable medium.
Computer-readable medium includes permanent and impermanency, removable and non-removable media can by any method or technology to realize information storage.Information can be computer-readable instruction, data structure, the module of program or other data.The example of the storage medium of computer includes, but it is not limited to phase transition internal memory (PRAM), static RAM (SRAM), dynamic random access memory (DRAM), other kinds of random access memory (RAM), read only memory (ROM), Electrically Erasable Read Only Memory (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc read only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tape, the storage of tape magnetic rigid disk or other magnetic storage apparatus or any other non-transmission medium, can be used for the information that storage can be accessed by a computing device.According to defining herein, computer-readable medium does not include temporary computer readable media (transitorymedia), such as data signal and the carrier wave of modulation.
It can further be stated that, term " includes ", " comprising " or its any other variant are intended to comprising of nonexcludability, so that include the process of a series of key element, method, commodity or equipment not only include those key elements, but also include other key elements being not expressly set out, or also include the key element intrinsic for this process, method, commodity or equipment.When there is no more restriction, statement " including ... " key element limited, it is not excluded that there is also other identical element in including the process of described key element, method, commodity or equipment.
It will be understood by those skilled in the art that embodiments herein can be provided as method, system or computer program.Therefore, the application can adopt the form of complete hardware embodiment, complete software implementation or the embodiment in conjunction with software and hardware aspect.And, the application can adopt the form at one or more upper computer programs implemented of computer-usable storage medium (including but not limited to disk memory, CD-ROM, optical memory etc.) wherein including computer usable program code.
The foregoing is only embodiments herein, be not limited to the application.To those skilled in the art, the application can have various modifications and variations.All make within spirit herein and principle any amendment, equivalent replacement, improvement etc., should be included within claims hereof scope.
Claims (12)
1. the palm detection method of a palm image, it is characterised in that including:
By palm image gray processing;
Extract the gradient orientation histogram HOG feature of the palm image of above-mentioned gray processing;
The HOG feature to described palm image of the support vector machines grader by training is classified;
Wherein, described SVM classifier is that the image beforehand through the image containing effective palm figure with containing invalid palm figure carries out classification based training and obtains.
2. the method for claim 1, it is characterised in that the described image containing effective palm figure includes: containing the image of complete palm figure, or enough carry out the image of most of palm area of personal recognition;Wherein, in the image containing effective palm figure, palm with wrist be fulcrum left-right rotation angular range for being not more than 90 degree;
The described image containing invalid palm figure includes: do not contain the image of palm figure, or the angle image more than 90 degree that palm is fulcrum left-right rotation with wrist, or contains only the image being not enough to carry out the palm area of personal recognition.
3. the method for claim 1, it is characterised in that extract the gradient orientation histogram HOG feature of the palm image of above-mentioned gray processing, specifically include:
By the palm compression of images of gray processing to specifying size, described appointment size includes 64 × 64 pixels;
HOG feature is extracted from the palm image after compression.
4. method as claimed in claim 3, it is characterised in that extract HOG feature from the palm image after compression, specifically include:
It is several unit by the palm image division after compression;
According to each unit divided, palm image upon compression determines several regions;
For each region, from each unit that this region comprises extract HOG feature, and by each unit from each region extract HOG Projection Character link up to the characteristic vector in the vector direction specified after, obtain the HOG characteristic vector that this region is corresponding;
The HOG characteristic vector that each region in palm image after compression obtains link up after HOG characteristic vector, as from compression after palm image in extract HOG characteristic vector.
5. method as claimed in claim 4, it is characterised in that when being sized to 64 × 64 pixel of palm image after compression, is several unit by the palm image division after compression, specifically includes:
Mode with each unit for 8*8 pixel, is several unit by the palm image division after compression.
6. method as claimed in claim 5, it is characterised in that according to each unit divided, determine several regions in palm image upon compression, specifically include:
In the way of every 2*2=4 unit is constituted a region, palm image upon compression being determined, several regions, the degree of overlapping between each region are 0.5.
7. method as claimed in claim 6, it is characterised in that on vector corresponding for the HOG Projection Character of extraction from each unit to specified angle scope, will specifically include:
By on the HOG Projection Character to 9 of the extraction vector by 0 degree to 180 degree of 9 deciles being divided into from each unit;
Determine that the 2*2*9=36 obtained by each region ties up the 7*7*36=1764 after HOG characteristic vector links up and ties up HOG characteristic vector, as extracting HOG characteristic vector from the palm image after compression.
8. the method as described in as arbitrary in claim 1~7, it is characterised in that the palm detection method of described palm image is applied in Palm Print Recognition System.
9. the palm detection system of a palm image, it is characterised in that including:
Gray shade unit, for by palm image gray processing;
HOG feature extraction unit, for being extracted its HOG feature from above-mentioned by the palm image after gray processing;
SVM classifier taxon, for calculating in the HOG feature of palm image whether have effective palm figure;
Output unit, for exporting the classification results of above-mentioned SVM classifier.
10. system as claimed in claim 9, it is characterised in that the described SVM classifier image beforehand through the image containing effective palm figure with containing invalid palm figure carries out classification based training and obtains a classifying face.
11. system as claimed in claim 10, it is characterised in that described SVM classifier is by calculating the HOG feature of palm image determines whether contain effective palm figure in palm image with above-mentioned classification relation of plane.
12. the system as described in claim 9~11, it is characterised in that the palm detection system of described palm image is applied in Palm Print Recognition System.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410816108.8A CN105787419A (en) | 2014-12-23 | 2014-12-23 | Palm detection method and palm detection system for palm image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410816108.8A CN105787419A (en) | 2014-12-23 | 2014-12-23 | Palm detection method and palm detection system for palm image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105787419A true CN105787419A (en) | 2016-07-20 |
Family
ID=56377477
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410816108.8A Pending CN105787419A (en) | 2014-12-23 | 2014-12-23 | Palm detection method and palm detection system for palm image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105787419A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107341473A (en) * | 2017-07-04 | 2017-11-10 | 深圳市利众信息科技有限公司 | Palm characteristic recognition method, palm characteristic identificating equipment and storage medium |
CN107766868A (en) * | 2016-08-15 | 2018-03-06 | 中国联合网络通信集团有限公司 | A kind of classifier training method and device |
CN108121350A (en) * | 2016-11-29 | 2018-06-05 | 腾讯科技(深圳)有限公司 | A kind of method and relevant apparatus for controlling aircraft landing |
CN108256533A (en) * | 2018-01-16 | 2018-07-06 | 南昌航空大学 | A kind of recognition methods of algae type and system |
CN110414330A (en) * | 2019-06-20 | 2019-11-05 | 平安科技(深圳)有限公司 | A kind of detection method and device of palm image |
CN113221892A (en) * | 2021-05-12 | 2021-08-06 | 佛山育脉科技有限公司 | Palm image determination method and device and computer readable storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102184404A (en) * | 2011-04-29 | 2011-09-14 | 汉王科技股份有限公司 | Method and device for acquiring palm region in palm image |
CN102402680A (en) * | 2010-09-13 | 2012-04-04 | 株式会社理光 | Hand and indication point positioning method and gesture confirming method in man-machine interactive system |
US20130170759A1 (en) * | 2007-11-29 | 2013-07-04 | Viewdle Inc. | Method and System of Person Identification by Facial Image |
CN104143074A (en) * | 2013-05-07 | 2014-11-12 | 李东舸 | Method and equipment for generating motion feature codes on the basis of motion feature information |
-
2014
- 2014-12-23 CN CN201410816108.8A patent/CN105787419A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130170759A1 (en) * | 2007-11-29 | 2013-07-04 | Viewdle Inc. | Method and System of Person Identification by Facial Image |
CN102402680A (en) * | 2010-09-13 | 2012-04-04 | 株式会社理光 | Hand and indication point positioning method and gesture confirming method in man-machine interactive system |
CN102184404A (en) * | 2011-04-29 | 2011-09-14 | 汉王科技股份有限公司 | Method and device for acquiring palm region in palm image |
CN104143074A (en) * | 2013-05-07 | 2014-11-12 | 李东舸 | Method and equipment for generating motion feature codes on the basis of motion feature information |
Non-Patent Citations (1)
Title |
---|
任彧等: ""基于HOG特征和SVM的手势识别"", 《科技通报》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107766868A (en) * | 2016-08-15 | 2018-03-06 | 中国联合网络通信集团有限公司 | A kind of classifier training method and device |
CN108121350A (en) * | 2016-11-29 | 2018-06-05 | 腾讯科技(深圳)有限公司 | A kind of method and relevant apparatus for controlling aircraft landing |
CN108121350B (en) * | 2016-11-29 | 2021-08-24 | 腾讯科技(深圳)有限公司 | Method for controlling aircraft to land and related device |
CN107341473A (en) * | 2017-07-04 | 2017-11-10 | 深圳市利众信息科技有限公司 | Palm characteristic recognition method, palm characteristic identificating equipment and storage medium |
CN108256533A (en) * | 2018-01-16 | 2018-07-06 | 南昌航空大学 | A kind of recognition methods of algae type and system |
CN110414330A (en) * | 2019-06-20 | 2019-11-05 | 平安科技(深圳)有限公司 | A kind of detection method and device of palm image |
CN113221892A (en) * | 2021-05-12 | 2021-08-06 | 佛山育脉科技有限公司 | Palm image determination method and device and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TWI687879B (en) | Server, client, user verification method and system | |
CN111191539B (en) | Certificate authenticity verification method and device, computer equipment and storage medium | |
CN105787419A (en) | Palm detection method and palm detection system for palm image | |
US7873189B2 (en) | Face recognition by dividing an image and evaluating a similarity vector with a support vector machine | |
CN104217203B (en) | Complex background card face information identifying method and system | |
US10395094B2 (en) | Method and apparatus for detecting glasses in a face image | |
CN106203333A (en) | Face identification method and system | |
CN104517104A (en) | Face recognition method and face recognition system based on monitoring scene | |
CN105631443B (en) | The update method and terminal device of fingerprint template | |
CN107316029B (en) | A kind of living body verification method and equipment | |
TW201606556A (en) | Method, device and system for identity authentication by using card features | |
JP2017522635A (en) | User authentication method, apparatus for executing the same, and recording medium storing the same | |
CN111275685A (en) | Method, device, equipment and medium for identifying copied image of identity document | |
CN111191568A (en) | Method, device, equipment and medium for identifying copied image | |
CN111626163B (en) | Human face living body detection method and device and computer equipment | |
CN112330331A (en) | Identity verification method, device and equipment based on face recognition and storage medium | |
JP7141518B2 (en) | Finger vein matching method, device, computer equipment, and storage medium | |
CN112232336A (en) | Certificate identification method, device, equipment and storage medium | |
CN106940804A (en) | Architectural engineering material management system form data method for automatically inputting | |
CN114386013A (en) | Automatic student status authentication method and device, computer equipment and storage medium | |
CN114049540A (en) | Method, device, equipment and medium for detecting marked image based on artificial intelligence | |
Rodríguez et al. | HD-MR: A new algorithm for number recognition in electrical meters | |
CN109492532A (en) | A kind of methods, devices and systems of image AI identification | |
CN112101296A (en) | Face registration method, face verification method, device and system | |
CN108985240B (en) | Method, apparatus, electronic device and storage medium for evaluating object detection algorithm |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1226517 Country of ref document: HK |
|
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160720 |
|
RJ01 | Rejection of invention patent application after publication | ||
REG | Reference to a national code |
Ref country code: HK Ref legal event code: WD Ref document number: 1226517 Country of ref document: HK |