WO2022104552A1 - 一种基于指静脉图像的认证方法、装置、设备和存储介质 - Google Patents
一种基于指静脉图像的认证方法、装置、设备和存储介质 Download PDFInfo
- Publication number
- WO2022104552A1 WO2022104552A1 PCT/CN2020/129480 CN2020129480W WO2022104552A1 WO 2022104552 A1 WO2022104552 A1 WO 2022104552A1 CN 2020129480 W CN2020129480 W CN 2020129480W WO 2022104552 A1 WO2022104552 A1 WO 2022104552A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- finger vein
- finger
- vein image
- image
- matched
- Prior art date
Links
- 210000003462 vein Anatomy 0.000 title claims abstract description 537
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000004590 computer program Methods 0.000 claims description 16
- 238000012795 verification Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 10
- 238000010586 diagram Methods 0.000 description 12
- 238000004891 communication Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 238000000605 extraction Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
Definitions
- the present invention relates to the technical field of image recognition, and in particular, to an authentication method, device, device and storage medium based on a finger vein image.
- identification technology is not only limited to traditional fingerprint, face, iris, etc., identification technology has been widely used, and finger vein identification technology has also emerged.
- the finger vein identification technology has high security and high stability, but in the existing finger vein identification technology, it is necessary to match the finger vein image to be identified with all the images in the database, and finally determine whether there is any image in the database that matches the finger vein image.
- the to-be-recognized image matches the image to determine whether other operations can be performed through the to-be-recognized finger vein image.
- the method for matching finger vein images to be identified has a large matching range and low matching efficiency, which causes the user to wait for a long time and reduces the user experience.
- Embodiments of the invention provide an authentication method, device, device and storage medium based on finger vein images, to solve the problems of large matching range and low matching efficiency of finger vein images to be identified in the existing finger vein identification technology.
- An embodiment of the present invention provides an authentication method based on a finger vein image, the method comprising:
- the first number, the second number and the sum value, the number of finger vein intersections, the number of finger vein endpoints and the total number corresponding to each finger vein image stored in advance determine the number of finger vein images to be identified corresponding to Finger vein image to be matched;
- the finger vein image to be matched it is determined whether the verification of the finger vein image to be recognized is passed.
- the described determination of the to-be-matched finger-vein image corresponding to the to-be-identified finger vein image comprises:
- the number of finger vein intersections, the number of finger vein endpoints and the total number corresponding to the pre-saved finger vein images, and the finger vein images corresponding to the first number, the second number and the sum value are determined to be the same as the finger vein image.
- the determining of the to-be-matched finger vein image corresponding to the finger vein image includes:
- the finger vein images with the same number of corresponding finger vein intersections as the first number in the pre-saved finger vein images are determined as the second to-be-matched finger-vein images corresponding to the to-be-identified finger vein images.
- determining the to-be-matched finger vein image corresponding to the to-be-identified finger vein image includes:
- determining the to-be-matched finger vein image corresponding to the to-be-identified finger vein image includes:
- the finger vein images whose total number is the same as the sum value in the pre-stored finger vein images are determined as the fourth to-be-matched finger-vein image corresponding to the to-be-identified finger vein image.
- An embodiment of the present invention further provides an authentication device based on a finger vein image, the device comprising:
- a processing module configured to determine a first number of finger vein intersections, a second number of finger vein endpoints, and a sum of the first number and the second number of the finger vein images to be identified;
- the identification module is used to determine the number of finger vein intersections, the number of finger vein endpoints and the total number corresponding to each finger vein image stored in advance according to the first quantity, the second quantity and the sum value to determine the to-be-identified The finger vein image to be matched corresponding to the finger vein image;
- a verification module configured to determine whether the to-be-recognized finger-vein image is verified according to the to-be-matched finger-vein image.
- the identification module is specifically used to compare the number of corresponding finger vein intersections, the number of finger vein endpoints and the total number in the pre-saved finger vein image with the first number, the second number and the sum value. Corresponding to the same finger vein image, it is determined as the first to-be-matched finger-vein image corresponding to the to-be-identified finger vein image.
- the identification module is specifically configured to determine the finger vein images with the same number of finger vein intersections as the first number in the pre-saved finger vein images as the second finger vein images corresponding to the to-be-identified finger vein images. Finger vein images to be matched.
- the identification module is specifically configured to determine as the to-be-identified finger vein image that the difference between the total number of the pre-saved finger vein images and the sum value is within a preset difference threshold range.
- the identification module is specifically configured to determine the finger vein images whose total number is the same as the sum value in the pre-saved finger vein images as the fourth finger vein to be matched corresponding to the finger vein image to be identified. image.
- An embodiment of the present invention further provides an electronic device, the electronic device includes at least a processor and a memory, and the processor is configured to implement the steps of any of the above-mentioned authentication methods based on a finger vein image when executing a computer program stored in the memory.
- An embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, implements the steps of any of the above-mentioned authentication methods based on a finger vein image.
- the embodiment of the present invention determines the first number of finger vein intersections, the second number of finger vein endpoints, and the sum of the first number and the second number in the finger vein image to be identified; according to the first number and the second number and the sum value, the number of finger vein intersections, the number of finger vein endpoints and the total number corresponding to each finger vein image saved in advance, determine the finger vein image to be matched corresponding to the finger vein image to be identified; according to the finger vein image to be matched image to determine whether the to-be-recognized finger vein image is verified.
- the finger vein image to be matched of the finger vein image to be identified is determined by the first number of finger vein intersections, the second number of finger vein endpoints and the sum value, and then based on the finger vein image to be identified
- the matching result is performed with the finger vein image to be matched, and then it is determined whether the finger vein image to be identified passes the verification, the matching range is narrowed, the matching efficiency is improved, and the user experience is improved.
- FIG. 1 is a schematic process diagram of an authentication method based on a finger vein image provided by an embodiment of the present invention
- FIG. 3 is a schematic flowchart of determining whether the to-be-recognized finger-vein image is verified according to the to-be-matched finger-vein image according to an embodiment of the present invention
- FIG. 4 is a schematic structural diagram of an authentication device based on a finger vein image provided by an embodiment of the present invention.
- FIG. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
- the embodiments of the present invention provide an authentication method, apparatus, device and medium based on the finger vein images.
- FIG. 1 is a schematic process diagram of an authentication method based on a finger vein image provided by an embodiment of the present invention, and the process includes the following steps:
- S101 Determine a first number of finger vein intersections, a second number of finger vein endpoints, and a sum of the first number and the second number in the finger vein image to be identified.
- An authentication method based on a finger vein image provided by an embodiment of the present invention is applied to an electronic device, and the electronic device may be a server, a PC client, a terminal device, and the like.
- a finger vein image to be identified to be matched it is necessary to obtain a first number of finger vein intersections, a second number of finger vein endpoints, and the relationship between the first number and the first number of the finger vein images to be identified. The sum of two quantities.
- the method for obtaining the first quantity and the second quantity may be: preprocessing the finger vein image to be identified, performing feature extraction on the preprocessed finger vein image, and determining the finger vein intersection after the feature extraction is completed; Finger vein endpoint.
- the preprocessing of the finger vein image to be identified may be to perform grayscale transformation on the finger vein image to be identified into a grayscale image; and then convert the grayscale transformed finger vein to be identified.
- the region of interest (ROI) extraction is performed on the image, that is, an image region is selected from the gray-scale transformed finger vein image to be identified as the focus of identification.
- the ROI area is an area containing finger veins; then, grayscale normalization, local grayscale histogram equalization and median filtering are performed on the ROI area to obtain the preprocessed Identify finger vein images.
- y represents the gray value of the finger vein image to be recognized after normalization
- x represents the gray value of the finger vein image to be recognized
- max and min represent the maximum gray value and the minimum gray value of the finger vein image. degree value.
- S102 Determine the to-be-identified finger vein image according to the first quantity, the second quantity, and the sum value, the number of finger vein intersections, the number of finger vein endpoints, and the total number corresponding to each finger vein image stored in advance The corresponding finger vein image to be matched.
- the electronic device pre-stores finger vein images, and the number of finger vein intersections, the number of finger vein endpoints, and the total number of finger vein intersections and finger vein endpoints in each finger vein image.
- the pre-saved finger vein images may be stored in a database, and the finger vein images may also be sorted according to the total number of finger vein intersections and finger vein endpoints, for example, the total number of finger vein images can be sorted by Sort from high to low. For finger vein images with the same total number, you can sort by the number of finger vein intersections, and for finger vein images with the same number of finger vein intersections, you can sort by the number of finger vein endpoints.
- the finger vein images to be matched may be finger vein images in which the difference between the total number and the sum is within a range of a preset difference threshold.
- S103 Determine, according to the finger vein image to be matched, whether the verification of the finger vein image to be identified is passed.
- the matching method between the finger vein image to be identified and the finger vein image to be matched may be matched by using the Hausdorff distance algorithm.
- the to-be-identified finger vein image is determined by determining the to-be-identified finger vein image to be matched, and then the to-be-identified finger vein image is matched with the to-be-matched finger vein image to determine the to-be-identified finger vein image to avoid
- the matching range is narrowed, the matching efficiency is improved, and the user's sense of use is improved.
- the determining the finger vein image to be matched corresponding to the finger vein image to be identified includes:
- the number of finger vein intersections, the number of finger vein endpoints and the total number corresponding to the pre-saved finger vein images, and the finger vein images corresponding to the first number, the second number and the sum value are determined to be the same as the finger vein image.
- the optimal finger vein image to be matched matched with the finger vein image to be matched is that the number of finger vein intersections of the finger vein image to be matched is the same as the finger vein to be identified.
- the first number of finger vein intersections in the image is the same, the number of finger vein endpoints is the same as the second number of finger vein endpoints in the finger vein image to be identified, and the total number is the same as the sum of the first number and the second number.
- the number of finger vein intersections, the number of finger vein endpoints, and the total number corresponding to each finger vein image saved in advance can be compared with the first number,
- the finger vein images corresponding to the second quantity and the sum value are determined to be the first finger vein images to be matched corresponding to the finger vein images to be identified.
- the first number of finger vein intersections in the finger vein image to be identified is 20, the second number of finger vein endpoints is 10, and the sum of the first number and the second number is 30.
- the finger vein image to be matched it can be preferentially determined that the number of finger vein intersections in the pre-saved finger vein images is 20, the number of finger vein endpoints is 10, and the total number of finger vein images is 30 finger vein images to be matched.
- this method is preferentially used to determine the finger vein images to be matched. If the finger vein images to be matched are identified based on this method, the subsequent finger vein images that meet other requirements may not be identified. Of course, in order to ensure accuracy, The following method can also be used to identify the finger vein image to be matched. But generally, after identifying the finger vein image to be matched by this method, it can be determined whether the finger vein image to be identified can be verified based on the finger vein image to be matched.
- FIG. 2 is a flowchart of matching finger veins to be identified according to an embodiment of the present invention. As shown in FIG. 2 , the process includes:
- S201 Receive a finger vein image to be identified.
- S202 Preprocess the to-be-identified finger vein image.
- S204 Determine the finger vein intersection and finger vein endpoint in the finger vein image to be identified.
- S205 Determine a first number of finger vein intersections, a second number of finger vein endpoints, and a sum of the first number and the second number in the finger vein image to be identified.
- S206 According to the first quantity, the second quantity and the sum value, the number of finger vein intersections, the number of finger vein endpoints and the total number corresponding to each finger vein image saved in advance, determine the finger vein to be matched corresponding to the finger vein image to be identified image.
- S207 According to the to-be-matched finger-vein image, determine whether the to-be-recognized finger vein image is verified.
- the determining the finger vein image to be matched corresponding to the finger vein image includes:
- the finger vein images with the same number of corresponding finger vein intersections as the first number in the pre-saved finger vein images are determined as the second to-be-matched finger-vein images corresponding to the to-be-identified finger vein images.
- the second selection of the finger vein image to be matched matched with the finger vein image to be identified is that the number of finger vein intersections in the finger vein image to be matched is the same as that of the finger vein image to be identified.
- the first number of finger vein intersections in the vein image is the same.
- the finger vein images that have the same number of finger vein intersections as the first number corresponding to each finger vein image saved in advance may be determined as the to-be-identified finger vein images.
- the first number of finger vein intersections in the finger vein image to be identified is 20, the second number of finger vein endpoints is 10, and the sum of the first number and the second number is 30.
- the finger vein image to be matched it can be determined that the number of finger vein intersections in the pre-saved finger vein images is 20 as the finger vein images to be matched.
- the method is used to determine the finger vein image to be matched. If the finger vein image to be identified is identified based on this method, the subsequent finger vein image that meets other requirements may not be identified. Of course, in order to ensure the accuracy, the following method can also be used to identify the finger vein image to be matched. However, generally after the finger vein image is identified by this method, it can be determined whether the finger vein image to be identified can be verified based on the finger vein image to be matched.
- the determining of the finger vein images to be matched corresponding to the finger vein images to be identified includes:
- the finger vein images whose total number is the same as the sum value in the pre-stored finger vein images are determined as the fourth to-be-matched finger-vein image corresponding to the to-be-identified finger vein image.
- the third selection of the to-be-matched finger-vein image to be matched with the to-be-identified finger vein image is: the number of finger vein intersections and the number of finger vein endpoints in the to-be-matched finger vein image
- the total number is the same as the sum of the first number and the second number.
- the finger vein junction number and the total number of finger vein end points corresponding to the finger vein image stored in advance can be used to determine the finger vein image with the same sum value.
- the vein image is determined as the fourth to-be-matched finger-vein image corresponding to the to-be-identified finger vein image.
- the first number of finger vein intersections in the finger vein image to be identified is 20, the second number of finger vein endpoints is 10, and the sum of the first number and the second number is 30.
- the finger vein images with a total number of 30 in the pre-saved finger vein images can be preferentially determined as the finger vein images to be matched, and the number of finger vein intersections in the finger vein images to be matched can be different from the first number, and the finger vein images of the finger vein images to be matched The number of endpoints can also be different from this second number.
- the method is used to determine the finger vein image to be matched. Based on the method, the finger vein image to be identified is identified. Based on the finger vein image to be matched, it can be determined whether the finger vein image to be identified can be verified.
- the identified finger vein image does not successfully match the to-be-matched finger-vein image identified based on this method, it means that there is no finger-vein image matching the to-be-identified finger-vein image in the pre-saved finger-vein image, and at this time the to-be-identified finger vein image Verification of vein image failed.
- the determining of the finger vein images to be matched corresponding to the finger vein images to be identified includes:
- the fourth selection of the to-be-matched finger-vein image to be matched with the to-be-identified finger vein image is: The difference between the total number of and the sum of the first number and the second number is within a preset difference threshold range.
- the difference between the sum of the corresponding number of finger vein intersections and the number of finger vein endpoints in the pre-saved finger vein image may be calculated. , determining a finger vein image whose difference is within a preset difference threshold range as the third to-be-matched finger-vein image corresponding to the to-be-identified finger vein image.
- the first number of finger vein intersections in the finger vein image to be identified is 20, the second number of finger vein endpoints is 10, the sum of the first number and the second number is 30, and the preset difference threshold is 3, That is, the preset difference threshold range is ⁇ 3.
- the finger vein images with a total number of 30 ⁇ 3 in the pre-stored finger vein images can be determined as the finger vein images to be matched, that is, the total number of finger vein images to be matched is determined.
- the finger vein images whose numbers are 27, 28, 29, 30, 31, 32, and 33 are the finger vein images to be matched.
- the number of endpoints can also be different from this second number.
- FIG. 3 is a schematic flowchart of determining whether the to-be-recognized finger-vein image is verified according to the to-be-matched finger-vein image provided by an embodiment of the present invention. As shown in FIG. 3 , the process includes:
- S301 Compare the number of finger vein intersections, the number of finger vein endpoints, and the total number corresponding to the finger vein image to be matched with the first number of finger vein intersections, the second number of finger vein endpoints, and the number of finger vein intersections in the finger vein image to be identified.
- the sum value corresponds to the same finger vein image to determine the first to-be-matched finger-vein image, and to determine whether the to-be-identified finger-vein image matches the first to-be-matched finger vein image; Then execute S302.
- S302 If the finger vein image to be identified does not match the first finger vein image to be matched, then the number of corresponding finger vein intersections in the finger vein image to be matched and the number of finger vein intersections in the finger vein image to be identified A second finger vein image to be matched is determined with the same number of finger vein images, and it is determined whether the finger vein image to be identified matches the second finger vein image to be matched. If the matching is successful, go to S306, and if the matching is unsuccessful, go to S306 S303.
- FIG. 4 is a schematic structural diagram of an authentication device based on a finger vein image provided by an embodiment of the present invention, where the device includes:
- a processing module 401 configured to determine the first number of finger vein intersections, the second number of finger vein endpoints, and the sum of the first number and the second number in the finger vein image to be identified;
- the identification module 402 is configured to determine the number of finger vein junctions, the number of finger vein endpoints and the total number corresponding to each finger vein image saved in advance according to the first number, the second number and the sum value. Identify the finger vein image to be matched corresponding to the finger vein image;
- the verification module 403 is configured to determine, according to the finger vein image to be matched, whether the verification of the finger vein image to be identified is passed.
- the identification module is specifically configured to compare the number of finger vein intersections, the number of finger vein endpoints, and the total number corresponding to the pre-saved finger vein images with the first number, the second The number and the sum value correspond to the same finger vein image, which is determined as the first to-be-matched finger-vein image corresponding to the to-be-identified finger vein image.
- the identification module is specifically configured to determine the finger vein images with the same number of finger vein intersections as the first number in the pre-saved finger vein images as the finger vein images to be identified.
- the second to-be-matched finger vein image corresponding to the vein image.
- the identification module is specifically configured to compare the finger vein images in which the difference between the corresponding total number in the pre-saved finger vein images and the sum value is within a preset difference threshold range It is determined to be the third to-be-matched finger-vein image corresponding to the to-be-identified finger vein image.
- the identifying module is specifically configured to determine the finger vein images whose total number is the same as the sum value in the pre-saved finger vein images as the finger vein images corresponding to the to-be-identified finger vein images.
- the fourth finger vein image to be matched.
- FIG. 5 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention.
- an embodiment of the present invention further provides an electronic device, as shown in FIG. 5 , including: a processor 501, a communication The interface 502, the memory 503 and the communication bus 504, wherein the processor 501, the communication interface 502, and the memory 503 complete the communication with each other through the communication bus 504;
- a computer program is stored in the memory 503, and when the program is executed by the processor 501, the processor 501 is caused to perform the following steps:
- the first number, the second number and the sum value, the number of finger vein intersections, the number of finger vein endpoints and the total number corresponding to each finger vein image stored in advance determine the number of finger vein images to be identified corresponding to Finger vein image to be matched;
- the finger vein image to be matched it is determined whether the verification of the finger vein image to be recognized is passed.
- the determining the to-be-matched finger vein image corresponding to the to-be-identified finger vein image includes:
- the number of finger vein intersections, the number of finger vein endpoints and the total number corresponding to the pre-saved finger vein images, and the finger vein images corresponding to the first number, the second number and the sum value are determined to be the same as the finger vein image.
- the determining the finger vein image to be matched corresponding to the finger vein image includes:
- the finger vein images with the same number of corresponding finger vein intersections as the first number in the pre-saved finger vein images are determined as the second to-be-matched finger-vein images corresponding to the to-be-identified finger vein images.
- the determining the to-be-matched finger vein image corresponding to the to-be-identified finger vein image includes:
- the determining the to-be-matched finger vein image corresponding to the to-be-identified finger vein image includes:
- the finger vein images whose total number is the same as the sum value in the pre-stored finger vein images are determined as the fourth to-be-matched finger-vein image corresponding to the to-be-identified finger vein image.
- the implementation of the above electronic device can refer to the implementation of the method, and the repetition will not be repeated.
- the communication bus mentioned in the above electronic device may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus or an Extended Industry Standard Architecture (Extended Industry Standard Architecture, EISA) bus or the like.
- PCI peripheral component interconnect standard
- EISA Extended Industry Standard Architecture
- the communication bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of presentation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.
- the communication interface 502 is used for communication between the above-mentioned electronic device and other devices.
- the memory may include random access memory (Random Access Memory, RAM), or may include non-volatile memory (Non-Volatile Memory, NVM), such as at least one disk storage.
- RAM Random Access Memory
- NVM Non-Volatile Memory
- the memory may also be at least one storage device located remotely from the aforementioned processor.
- the above-mentioned processor can be a general-purpose processor, including a central processing unit, a network processor (NP), etc.; it can also be a digital instruction processor (Digital Signal Processing, DSP), an application-specific integrated circuit, a field programmable gate array, or Other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
- DSP Digital Signal Processing
- embodiments of the present invention further provide a computer-readable storage medium, where a computer program executable by a processor is stored in the computer-readable storage medium.
- the processor When running on the processor, the processor implements the following steps when executing:
- the first number, the second number and the sum value, the number of finger vein intersections, the number of finger vein endpoints and the total number corresponding to each finger vein image stored in advance determine the number of finger vein images to be identified corresponding to Finger vein image to be matched;
- the finger vein image to be matched it is determined whether the verification of the finger vein image to be recognized is passed.
- the determining the to-be-matched finger vein image corresponding to the to-be-identified finger vein image includes:
- the number of finger vein intersections, the number of finger vein endpoints and the total number corresponding to the pre-saved finger vein images, and the finger vein images corresponding to the first number, the second number and the sum value are determined to be the same as the finger vein image.
- the determining the finger vein image to be matched corresponding to the finger vein image includes:
- the finger vein images with the same number of corresponding finger vein intersections as the first number in the pre-saved finger vein images are determined as the second to-be-matched finger-vein images corresponding to the to-be-identified finger vein images.
- the determining the to-be-matched finger vein image corresponding to the to-be-identified finger vein image includes:
- the determining the to-be-matched finger vein image corresponding to the to-be-identified finger vein image includes:
- the finger vein images whose total number is the same as the sum value in the pre-stored finger vein images are determined as the fourth to-be-matched finger-vein image corresponding to the to-be-identified finger vein image.
- embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
- computer-usable storage media including, but not limited to, disk storage, CD-ROM, optical storage, etc.
- These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions
- the apparatus implements the functions specified in the flow or flows of the flowcharts and/or the block or blocks of the block diagrams.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
本发明实施例提供了一种基于指静脉图像的认证方法、装置、设备和存储介质，由于本发明实施例确定待识别指静脉图像的指静脉交叉点的第一数量、指静脉端点的第二数量以及该第一数量和第二数量的和值；根据该第一数量、第二数量以及该和值，预先保存的每个指静脉图像对应的指静脉交叉点数量、指静脉端点数量以及总数量，确定该待识别指静脉图像对应的待匹配指静脉图像；根据该待匹配指静脉图像，确定该待识别指静脉图像是否验证通过，在本发明实施例中，缩小了匹配范围，提高了匹配效率，提高了用户的使用体验。
Description
本发明涉及图像识别技术领域，尤其涉及一种基于指静脉图像的认证方法、装置、设备和存储介质。
随着科学技术的发展，识别技术不仅仅局限于传统的指纹、人脸、虹膜等，识别技术已经被广泛应用，还兴起了指静脉识别技术。其中该指静脉识别技术具有高安全性和高稳定性，但是现有的指静脉识别技术中，需要将待识别指静脉图像与数据库中的所有图像进行匹配，最终确定该数据库中是否有与该待识别图像匹配的图像，从而确定是否可以通过该待识别指静脉图像进行其他操作。在现有技术中，该待识别指静脉图像进行匹配的方法，匹配范围大，匹配效率低，造成用户长时间的等待，降低了用户的使用体验。
发明内容
发明实施例提供了一种基于指静脉图像的认证方法、装置、设备和存储介质，用以解决现有的指静脉识别技术中待识别指静脉图像的匹配范围大，匹配效率低的问题。
本发明实施例提供一种基于指静脉图像的认证方法，所述方法包括：
确定待识别指静脉图像的指静脉交叉点的第一数量、指静脉端点的第二数量以及所述第一数量和第二数量的和值；
根据所述第一数量、第二数量以及所述和值，预先保存的每个指静脉图像对应的指静脉交叉点数量、指静脉端点数量以及总数量，确定所述待识别指静脉图像对应的待匹配指静脉图像；
根据所述待匹配指静脉图像，确定所述待识别指静脉图像是否验证通过。
进一步地，所述确定所述待识别指静脉图像对应的待匹配指静脉图像包 括：
将预先保存的指静脉图像中对应的指静脉交叉点数量、指静脉端点数量以及总数量，与所述第一数量、第二数量以及所述和值对应相同的指静脉图像，确定为所述待识别指静脉图像对应的第一待匹配指静脉图像。
进一步地，所述确定所述指静脉图像对应的待匹配指静脉图像包括：
将预先保存的指静脉图像中对应的指静脉交叉点数量与所述第一数量相同的指静脉图像确定为所述待识别指静脉图像对应的第二待匹配指静脉图像。
进一步地，所述确定所述待识别指静脉图像对应的待匹配指静脉图像包括：
将预先保存的指静脉图像中对应的总数量与所述和值的差值在预设的差值阈值范围内的指静脉图像确定为所述待识别指静脉图像对应的第三待匹配指静脉图像。
进一步地，所述确定所述待识别指静脉图像对应的待匹配指静脉图像包括：
将预先保存的指静脉图像中对应的总数量与所述和值相同的指静脉图像确定为所述待识别指静脉图像对应的第四待匹配指静脉图像。
本发明实施例还提供一种基于指静脉图像的认证装置，所述装置包括：
处理模块，用于确定待识别指静脉图像的指静脉交叉点的第一数量、指静脉端点的第二数量以及所述第一数量和第二数量的和值；
识别模块，用于根据所述第一数量、第二数量以及所述和值，预先保存的每个指静脉图像对应的指静脉交叉点数量、指静脉端点数量以及总数量，确定所述待识别指静脉图像对应的待匹配指静脉图像；
验证模块，用于根据所述待匹配指静脉图像，确定所述待识别指静脉图像是否验证通过。
进一步地，所述识别模块，具体用于将预先保存的指静脉图像中对应的指静脉交叉点数量、指静脉端点数量以及总数量，与所述第一数量、第二数量以及所述和值对应相同的指静脉图像，确定为所述待识别指静脉图像对应 的第一待匹配指静脉图像。
进一步地，所述识别模块，具体用于将预先保存的指静脉图像中对应的指静脉交叉点数量与所述第一数量相同的指静脉图像确定为所述待识别指静脉图像对应的第二待匹配指静脉图像。
进一步地，所述识别模块，具体用于将预先保存的指静脉图像中对应的总数量与所述和值的差值在预设的差值阈值范围内的指静脉图像确定为所述待识别指静脉图像对应的第三待匹配指静脉图像。
进一步地，所述识别模块，具体用于将预先保存的指静脉图像中对应的总数量与所述和值相同的指静脉图像确定为所述待识别指静脉图像对应的第四待匹配指静脉图像。
本发明实施例还提供一种电子设备，所述电子设备至少包括处理器和存储器，所述处理器用于执行存储器中存储的计算机程序时实现上述任一的基于指静脉图像的认证方法的步骤。
本发明实施例还提供一种计算机可读存储介质，其存储有计算机程序，所述计算机程序被处理器执行时实现上述任一的基于指静脉图像的认证方法的步骤。
由于本发明实施例确定待识别指静脉图像的指静脉交叉点的第一数量、指静脉端点的第二数量以及该第一数量和第二数量的和值；根据该第一数量、第二数量以及该和值，预先保存的每个指静脉图像对应的指静脉交叉点数量、指静脉端点数量以及总数量，确定该待识别指静脉图像对应的待匹配指静脉图像；根据该待匹配指静脉图像，确定该待识别指静脉图像是否验证通过。在本发明实施例中，是通过指静脉交叉点的第一数量，指静脉端点的第二数量以及和值，确定待识别指静脉图像的待匹配指静脉图像，再基于该待识别指静脉图像与该待匹配指静脉图像进行匹配结果，进而确定该待识别指静脉图像是否验证通过，缩小了匹配范围，提高了匹配效率，提高了用户的使用体验。
图1为本发明实施例提供的一种基于指静脉图像的认证方法的过程示意图；
图2为本发明实施例提供的对待识别指静脉进行匹配的流程图；
图3为本发明实施例提供的根据该待匹配指静脉图像，确定该待识别指静脉图像是否验证通过的流程示意图；
图4为本发明实施例提供的一种基于指静脉图像的认证装置的结构示意图；
图5为本发明实施例提供的一种电子设备结构示意图。
为了使本发明的目的、技术方案和优点更加清楚，下面将结合附图对本发明作进一步地详细描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例，都属于本发明保护的范围。
为了提高待识别指静脉图像的匹配效率，本发明实施例提供了一种基于指静脉图像的认证方法、装置、设备及介质。
实施例1：
图1为本发明实施例提供的一种基于指静脉图像的认证方法的过程示意图，该过程包括以下步骤：
S101：确定待识别指静脉图像的指静脉交叉点的第一数量、指静脉端点的第二数量以及所述第一数量和第二数量的和值。
本发明实施例提供的一种基于指静脉图像的认证方法应用于电子设备，该电子设备可以是服务器、PC客户端、终端设备等。
在本发明实施例中，对于要进行匹配的待识别指静脉图像，需要获取该待识别指静脉图像的指静脉交叉点的第一数量、指静脉端点的第二数量以及 该第一数量与第二数量的和值。
其中，获取该第一数量和第二数量的方法可以是，对该待识别指静脉图像进行预处理，在将预处理后的指静脉图像进行特征提取，特征提取完成后确定指静脉交叉点以及指静脉端点。
具体的，在本发明实施例中，对该待识别指静脉图像进行预处理可以是将该待识别指静脉图像进行灰度变换转化为灰度图像；再对灰度变换后的待识别指静脉图像进行感兴趣区域(Region Of Interest，ROI)提取，即从该灰度变换后的待识别指静脉图像中选择一个图像区域作为识别的重点。在本发明实施例中，该ROI区域为含有指静脉的区域；然后对该ROI区域进行灰度归一化处理，以及局部灰度直方图均衡化和中值滤波，得到经过预处理后的待识别指静脉图像。
其中，在进行灰度归一化处理时，可以采用如下公式：
y＝((x–min)*255)/(max–min)
在该公式中，y表示归一化之后的待识别指静脉图像的灰度值，x表示待识别指静脉图像的灰度值，max和min表示该指静脉图像的最大灰度值和最小灰度值。
在本发明实施例中，对该待识别指静脉图像进行预处理后，将对预处理后的待识别指静脉图像进行特征提取。具体的，先提取该预处理后的待识别指静脉图像中的谷形区域，为了确定每个像素的脊线方向，以该像素为中心的9*9窗口内，分别计算与之对应的8个方向上的算子的卷积F(i)(i＝1,2,…8),然后得到这8个方向上的最大卷积和(Gmax)，把Gmax作为该点新的灰度值，其中，Gmax＝Max(F(i))(i＝1,2,…8)；提取谷形区域后，进行两次阈值分割，得到一个二进制的待识别指静脉图像；再进行中值滤波，过滤掉该待识别指静脉图像中的噪点；对该待识别指静脉图像进行细化，并去除掉指静脉的毛刺，得到特征提取后的待识别指静脉图像。
得到特征提取后的待识别指静脉图像之后，可以确定该待识别指静脉图像的交叉点和端点。例如，在3*3的邻域内，以I0为中心点，围绕中心点的 八个点，顺时针标号I1，I2…I8,若I0＝1，计算在二进制待识别指静脉图像中I1，I2…I8的0和1的交替变换次数，若次数大于等于6时，则将该I0点标记为指静脉交叉点，若次数等于2时，则将该I0点标记为指静脉端点。
S102：根据所述第一数量、第二数量以及所述和值，预先保存的每个指静脉图像对应的指静脉交叉点数量、指静脉端点数量以及总数量，确定所述待识别指静脉图像对应的待匹配指静脉图像。
在本发明实施例中，电子设备中预先保存有指静脉图像，以及每张指静脉图像中的指静脉交叉点数量、指静脉端点数量以及指静脉交叉点和指静脉端点的总数量。在本发明实施例中，该预先保存的指静脉图像可以保存在数据库中，并且，还可以将这些指静脉图像按照指静脉交叉点和指静脉端点的总数量进行排序，例如可以按照总数量由高到低进行排序，对于总数量相同的指静脉图像，可以按照指静脉交叉点数量，对于指教脉交叉点数量相同的指静脉图像，可以按照指静脉端点数量进行排序。在确定了待识别指静脉图像的指静脉交叉点的第一数量、指静脉端点的第二数量以及第一数量与第二数量的和值之后，可以根据该第一数量、第二数量以及和值，预先保存的每个指静脉图像对应的指静脉交叉点数量、指静脉端点数量以及总数量，确定该待识别指静脉图像对应的待匹配指静脉图像。
在本发明实施例中，该待匹配指静脉图像可以是总数量与该和值的差值在预设差值阈值的范围内的指静脉图像。
S103：根据所述待匹配指静脉图像，确定所述待识别指静脉图像是否验证通过。
在确定了待匹配指静脉图像之后，需要将待匹配指静脉图像与该待识别指静脉图像进行匹配，若匹配成功，则确定该待识别指静脉图像验证通过，若匹配未成功，则确定该待识别指静脉图像验证失败。
其中，该待识别指静脉图像与该待匹配指静脉图像的匹配方法可以采用Hausdorff距离算法进行匹配。
在本发明实施例中，是通过确定待识别指静脉图像的待匹配指静脉图像， 再对该待识别指静脉图像与该待匹配指静脉图像进行匹配，进而确定该待识别指静脉图像，避免了将待识别指静脉图像与数据库中的所有指静脉图像进行匹配，缩小了匹配范围，提高了匹配效率，提高了用户的使用感。
实施例2：
为了确定待匹配指静脉图像，提高匹配效率，在上述实施例的基础上，在本发明实施例中，所述确定所述待识别指静脉图像对应的待匹配指静脉图像包括：
将预先保存的指静脉图像中对应的指静脉交叉点数量、指静脉端点数量以及总数量，与所述第一数量、第二数量以及所述和值对应相同的指静脉图像，确定为所述待识别指静脉图像对应的第一待匹配指静脉图像。
在本发明实施例中，为了进一步提高匹配效率，最优的与该待匹配指静脉图像匹配的待匹配指静脉图像是，该待匹配指静脉图像的指静脉交叉点数量与该待识别指静脉图像中的指静脉交叉点的第一数量相同，指静脉端点数量与该待识别指静脉图像中指静脉端点的第二数量相同，以及总数量与该第一数量与第二数量的和值相同。
因此，在本发明实施例中，在确定待匹配指静脉图像时，可以根据预先保存的每个指静脉图像对应的指静脉交叉点数量、指静脉端点数量以及总数量，与该第一数量、第二数量以及该和值对应相同的指静脉图像确定为该待识别指静脉图像对应的第一待匹配指静脉图像。
例如，待识指静脉图像中指静脉交叉点的第一数量为20，指静脉端点的第二数量为10，该第一数量与第二数量的和值为30，在确定待匹配指静脉图像时，可以优先确定预先保存的指静脉图像中指静脉交叉点数量为20，指静脉端点数量为10，总数量为30的指静脉图像为待匹配指静脉图像。
在本发明实施例中优先采用该方法确定待匹配指静脉图像，如果基于该方法识别到了待匹配指静脉图像，则可以不再继续识别后续满足其他要求的指静脉图像，当然为了保证准确性，还可以是采用下述方法识别待匹配指静脉图像。但一般通过该方法识别到待匹配指静脉图像后，基于该待匹配指静 脉图像即可确定该待识别指静脉图像是否能够验证通过。
图2为本发明实施例提供的对待识别指静脉进行匹配的流程图，如图2所示，该过程包括：
S201：接收待识别指静脉图像。
S202：对该待识别指静脉图像进行预处理。
S203：对该待识别指静脉图像进行模板骨架提取。
S204：确定该待识别指静脉图像中的指静脉交叉点和指静脉端点。
S205：确定该待识别指静脉图像的指静脉交叉点的第一数量，指静脉端点的第二数量，以及该第一数量和第二数量的和值。
S206：根据第一数量、第二数量以及和值，预先保存的每个指静脉图像对应的指静脉交叉点数量、指静脉端点数量以及总数量，确定待识别指静脉图像对应的待匹配指静脉图像。
S207：根据该待匹配指静脉图像，确定该待识别指静脉图像是否验证通过。
为了确定待匹配指静脉图像，提高匹配效率，在上述各实施例的基础上，所述确定所述指静脉图像对应的待匹配指静脉图像包括：
将预先保存的指静脉图像中对应的指静脉交叉点数量与所述第一数量相同的指静脉图像确定为所述待识别指静脉图像对应的第二待匹配指静脉图像。
在本发明实施例中，为了进一步提高匹配效率，与该待识别指静脉图像匹配的待匹配指静脉图像的第二选择是，该待匹配指静脉图像的指静脉交叉点数量与该待识别指静脉图像中的指静脉交叉点的第一数量相同。
因此，在本发明实施例中，在确定待匹配指静脉图像时，可以根据预先保存的每个指静脉图像对应的指静脉交叉点数量与该第一数量相同的指静脉图像确定为该待识别指静脉图像对应的第二待匹配指静脉图像。
例如，待识指静脉图像中指静脉交叉点的第一数量为20，指静脉端点的第二数量为10，该第一数量与第二数量的和值为30，在确定待匹配指静脉图像时，可以确定预先保存的指静脉图像中指静脉交叉点数量为20的指静脉图 像为待匹配指静脉图像。
在本发明实施例中采用该方法确定待匹配指静脉图像，如果基于该方法识别到了待识别指静脉图像，则可以不再继续识别后续满足其他要求的指静脉图像。当然为了保证准确性，还可以是采用下述方法识别待匹配指静脉图像。但是一般通过该方法识别到指静脉图像后，基于该待匹配指静脉图像即可确定该待识别指静脉图像是否能够验证通过。
为了确定待匹配指静脉图像，提高匹配效率，在上述各实施例的基础上，所述确定所述待识别指静脉图像对应的待匹配指静脉图像包括：
将预先保存的指静脉图像中对应的总数量与所述和值相同的指静脉图像确定为所述待识别指静脉图像对应的第四待匹配指静脉图像。
在本发明实施例中，为了进一步提高匹配效率，与该待识别指静脉图像匹配的待匹配指静脉图像的第三选择是，该待匹配指静脉图像的指静脉交叉点数量与指静脉端点数量的总数量与该第一数量与第二数量的和值相同。
因此，在本发明实施例中，在确定待匹配指静脉图像时，可以根据预先保存的指静脉图像中对应的指静脉交叉点数量和指静脉端点数量的总数量，与该和值相同的指静脉图像确定为该待识别指静脉图像对应的第四待匹配指静脉图像。
例如，待识指静脉图像中指静脉交叉点的第一数量为20，指静脉端点的第二数量为10，该第一数量与第二数量的和值为30，在确定待匹配指静脉图像时，可以优先确定预先保存的指静脉图像中总数量为30的指静脉图像为待匹配指静脉图像，该待匹配指静脉图像中的指静脉交叉点数量可以与该第一数量不同，其指静脉端点数量也可以与该第二数量不同。
在本发明实施例中采用该方法确定待匹配指静脉图像，基于该方法识别到了待识别指静脉图像，基于该待匹配指静脉图像即可确定该待识别指静脉图像是否能够验证通过，如果待识别指静脉图像没有与基于该方法识别到的待匹配指静脉图像匹配成功，则说明预先保存的指静脉图像中不存在与该待识别指静脉图像匹配的指静脉图像，此时该待识别指静脉图像验证失败。
为了确定待匹配指静脉图像，提高匹配效率，在上述各实施例的基础上，所述确定所述待识别指静脉图像对应的待匹配指静脉图像包括：
将预先保存的指静脉图像中对应的总数量与所述和值的差值在预设的差值阈值范围内的指静脉图像确定为所述待识别指静脉图像对应的第三待匹配指静脉图像。
在本发明实施例中，为了进一步提高匹配效率，与该待识别指静脉图像匹配的待匹配指静脉图像的第四选择是，该待匹配指静脉图像的指静脉交叉点数量与指静脉端点数量的总数量与该第一数量与第二数量的和值的差值在预设的差值阈值范围内。
因此，在本发明实施例中，在确定待匹配指静脉图像时，可以计算预先保存的指静脉图像中对应的指静脉交叉点数量和指静脉端点数量的总数量，与该和值的差值，确定差值在预设的差值阈值范围内的指静脉图像为该待识别指静脉图像对应的第三待匹配指静脉图像。
例如，待识指静脉图像中指静脉交叉点的第一数量为20，指静脉端点的第二数量为10，该第一数量与第二数量的和值为30，预设的差值阈值3，即预设的差值阈值范围为±3，在确定待匹配指静脉图像时，可以确定预先保存的指静脉图像中总数量为30±3的指静脉图像为待匹配指静脉图像，即确定总数量为27、28、29、30、31、32、33的指静脉图像为待匹配指静脉图像，该待匹配指静脉图像中的指静脉交叉点数量可以与该第一数量不同，其指静脉端点数量也可以与该第二数量不同。
图3为本发明实施例提供的根据该待匹配指静脉图像，确定该待识别指静脉图像是否验证通过的流程示意图，如图3所示，该过程包括：
S301：将该待匹配指静脉图像中对应的指静脉交叉点数量、指静脉端点数量以及总数量，与待识别指静脉图像的指静脉交叉点的第一数量、指静脉端点的第二数量以及该和值对应相同的指静脉图像确定第一待匹配指静脉图像，确定该待识别指静脉图像是否与该第一待匹配指静脉图像匹配，若匹配成功，则执行S306，若匹配不成功，则执行S302。
S302：若该待识别指静脉图像与该第一待匹配指静脉图像不匹配，则将该待匹配指静脉图像中对应的指静脉交叉点数量与待识别指静脉图像的指静脉交叉点的第一数量相同的指静脉图像确定第二待匹配指静脉图像，确定该待识别指静脉图像是否与该第二待匹配指静脉图像匹配，若匹配成功，则执行S306，若匹配不成功，则执行S303。
S303：若该待识别指静脉图像与该第二待匹配指静脉图像不匹配，则将该待匹配指静脉图像中对应的指静脉交叉点数量和指静脉端点数量的总数量与待识别指静脉图像的和值相同的指静脉图像确定第三待匹配指静脉图像，确定该待识别指静脉图像是否与该第三待匹配指静脉图像匹配，若匹配成功，则执行S306，若匹配不成功，则执行S304。
S304：若该待识别指静脉图像与该第三待匹配指静脉图像不匹配，则将该待匹配指静脉图像中对应的指静脉交叉点数量和指静脉端点数量的总数量与待识别指静脉图像的和值的差值在预设的差值阈值范围内的指静脉图像确定第四待匹配指静脉图像，确定该待识别指静脉图像是否与该第四待匹配指静脉图像匹配，若匹配成功，则执行S306，若匹配不成功，则执行S305。
S305：确定该待识别指静脉图像验证不通过。
S306：确定该待识别指静脉图像验证通过。
实施例3：
图4为本发明实施例提供的一种基于指静脉图像的认证装置的结构示意图，该装置包括：
处理模块401，用于确定待识别指静脉图像的指静脉交叉点的第一数量、指静脉端点的第二数量以及所述第一数量和第二数量的和值；
识别模块402，用于根据所述第一数量、第二数量以及所述和值，预先保存的每个指静脉图像对应的指静脉交叉点数量、指静脉端点数量以及总数量，确定所述待识别指静脉图像对应的待匹配指静脉图像；
验证模块403，用于根据所述待匹配指静脉图像，确定所述待识别指静脉图像是否验证通过。
在一种可能的实施方式中，所述识别模块，具体用于将预先保存的指静脉图像中对应的指静脉交叉点数量、指静脉端点数量以及总数量，与所述第一数量、第二数量以及所述和值对应相同的指静脉图像，确定为所述待识别指静脉图像对应的第一待匹配指静脉图像。
在一种可能的实施方式中，所述识别模块，具体用于将预先保存的指静脉图像中对应的指静脉交叉点数量与所述第一数量相同的指静脉图像确定为所述待识别指静脉图像对应的第二待匹配指静脉图像。
在一种可能的实施方式中，所述识别模块，具体用于将预先保存的指静脉图像中对应的总数量与所述和值的差值在预设的差值阈值范围内的指静脉图像确定为所述待识别指静脉图像对应的第三待匹配指静脉图像。
在一种可能的实施方式中，所述识别模块，具体用于将预先保存的指静脉图像中对应的总数量与所述和值相同的指静脉图像确定为所述待识别指静脉图像对应的第四待匹配指静脉图像。
实施例4：
图5为本发明实施例提供的一种电子设备结构示意图，在上述各实施例的基础上，本发明实施例还提供了一种电子设备，如图5所示，包括：处理器501、通信接口502、存储器503和通信总线504，其中，处理器501，通信接口502，存储器503通过通信总线504完成相互间的通信；
所述存储器503中存储有计算机程序，当所述程序被所述处理器501执行时，使得所述处理器501执行如下步骤：
确定待识别指静脉图像的指静脉交叉点的第一数量、指静脉端点的第二数量以及所述第一数量和第二数量的和值；
根据所述第一数量、第二数量以及所述和值，预先保存的每个指静脉图像对应的指静脉交叉点数量、指静脉端点数量以及总数量，确定所述待识别指静脉图像对应的待匹配指静脉图像；
根据所述待匹配指静脉图像，确定所述待识别指静脉图像是否验证通过。
在一种可能的实施方式中，所述确定所述待识别指静脉图像对应的待匹 配指静脉图像包括：
将预先保存的指静脉图像中对应的指静脉交叉点数量、指静脉端点数量以及总数量，与所述第一数量、第二数量以及所述和值对应相同的指静脉图像，确定为所述待识别指静脉图像对应的第一待匹配指静脉图像。
在一种可能的实施方式中，所述确定所述指静脉图像对应的待匹配指静脉图像包括：
将预先保存的指静脉图像中对应的指静脉交叉点数量与所述第一数量相同的指静脉图像确定为所述待识别指静脉图像对应的第二待匹配指静脉图像。
在一种可能的实施方式中，所述确定所述待识别指静脉图像对应的待匹配指静脉图像包括：
将预先保存的指静脉图像中对应的总数量与所述和值的差值在预设的差值阈值范围内的指静脉图像确定为所述待识别指静脉图像对应的第三待匹配指静脉图像。
在一种可能的实施方式中，所述确定所述待识别指静脉图像对应的待匹配指静脉图像包括：
将预先保存的指静脉图像中对应的总数量与所述和值相同的指静脉图像确定为所述待识别指静脉图像对应的第四待匹配指静脉图像。
由于上述电子设备解决问题的原理与基于指静脉图像的认证相似，因此上述电子设备的实施可以参见方法的实施，重复之处不再赘述。
上述电子设备提到的通信总线可以是外设部件互连标准(Peripheral Component Interconnect，PCI)总线或扩展工业标准结构(Extended Industry Standard Architecture，EISA)总线等。该通信总线可以分为地址总线、数据总线、控制总线等。为便于表示，图中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
通信接口502用于上述电子设备与其他设备之间的通信。
存储器可以包括随机存取存储器(Random Access Memory，RAM)，也可以包括非易失性存储器(Non-Volatile Memory，NVM)，例如至少一个磁盘存 储器。可选地，存储器还可以是至少一个位于远离前述处理器的存储装置。
上述处理器可以是通用处理器，包括中央处理器、网络处理器(Network Processor，NP)等；还可以是数字指令处理器(Digital Signal Processing，DSP)、专用集成电路、现场可编程门陈列或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。
实施例5：
在上述各实施例的基础上，本发明实施例还提供了一种计算机可读存储介质，所述计算机可读存储介质内存储有可由处理器执行的计算机程序，当所述程序在所述处理器上运行时，使得所述处理器执行时实现如下步骤：
确定待识别指静脉图像的指静脉交叉点的第一数量、指静脉端点的第二数量以及所述第一数量和第二数量的和值；
根据所述第一数量、第二数量以及所述和值，预先保存的每个指静脉图像对应的指静脉交叉点数量、指静脉端点数量以及总数量，确定所述待识别指静脉图像对应的待匹配指静脉图像；
根据所述待匹配指静脉图像，确定所述待识别指静脉图像是否验证通过。
在一种可能的实施方式中，所述确定所述待识别指静脉图像对应的待匹配指静脉图像包括：
将预先保存的指静脉图像中对应的指静脉交叉点数量、指静脉端点数量以及总数量，与所述第一数量、第二数量以及所述和值对应相同的指静脉图像，确定为所述待识别指静脉图像对应的第一待匹配指静脉图像。
在一种可能的实施方式中，所述确定所述指静脉图像对应的待匹配指静脉图像包括：
将预先保存的指静脉图像中对应的指静脉交叉点数量与所述第一数量相同的指静脉图像确定为所述待识别指静脉图像对应的第二待匹配指静脉图像。
在一种可能的实施方式中，所述确定所述待识别指静脉图像对应的待匹配指静脉图像包括：
将预先保存的指静脉图像中对应的总数量与所述和值的差值在预设的差 值阈值范围内的指静脉图像确定为所述待识别指静脉图像对应的第三待匹配指静脉图像。
在一种可能的实施方式中，所述确定所述待识别指静脉图像对应的待匹配指静脉图像包括：
将预先保存的指静脉图像中对应的总数量与所述和值相同的指静脉图像确定为所述待识别指静脉图像对应的第四待匹配指静脉图像。
由于上述提供的计算机可读取介质解决问题的原理与基于指静脉图像的认证方法相似，因此处理器执行上述计算机可读取介质中的计算机程序后，实现的步骤可以参见上述其他实施例，重复之处不再赘述。
本领域内的技术人员应明白，本发明的实施例可提供为方法、系统、或计算机程序产品。因此，本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本发明是参照根据本发明的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的 处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
显然，本领域的技术人员可以对本发明进行各种改动和变型而不脱离本发明的精神和范围。这样，倘若本发明的这些修改和变型属于本发明权利要求及其等同技术的范围之内，则本发明也意图包含这些改动和变型在内。
Claims (10)
- 一种基于指静脉图像的认证方法，其特征在于，所述方法包括：确定待识别指静脉图像的指静脉交叉点的第一数量、指静脉端点的第二数量以及所述第一数量和第二数量的和值；根据所述第一数量、第二数量以及所述和值，预先保存的每个指静脉图像对应的指静脉交叉点数量、指静脉端点数量以及总数量，确定所述待识别指静脉图像对应的待匹配指静脉图像；根据所述待匹配指静脉图像，确定所述待识别指静脉图像是否验证通过。
- 根据权利要求1所述的方法，其特征在于，所述确定所述待识别指静脉图像对应的待匹配指静脉图像包括：将预先保存的指静脉图像中对应的指静脉交叉点数量、指静脉端点数量以及总数量，与所述第一数量、第二数量以及所述和值对应相同的指静脉图像，确定为所述待识别指静脉图像对应的第一待匹配指静脉图像。
- 根据权利要求1或2所述的方法，其特征在于，所述确定所述指静脉图像对应的待匹配指静脉图像包括：将预先保存的指静脉图像中对应的指静脉交叉点数量与所述第一数量相同的指静脉图像确定为所述待识别指静脉图像对应的第二待匹配指静脉图像。
- 根据权利要求3所述的方法，其特征在于，所述确定所述待识别指静脉图像对应的待匹配指静脉图像包括：将预先保存的指静脉图像中对应的总数量与所述和值的差值在预设的差值阈值范围内的指静脉图像确定为所述待识别指静脉图像对应的第三待匹配指静脉图像。
- 根据权利要求4所述的方法，其特征在于，所述确定所述待识别指静脉图像对应的待匹配指静脉图像包括：将预先保存的指静脉图像中对应的总数量与所述和值相同的指静脉图像确定为所述待识别指静脉图像对应的第四待匹配指静脉图像。
- 一种基于指静脉图像的认证装置，其特征在于，所述装置包括：处理模块，用于确定待识别指静脉图像的指静脉交叉点的第一数量、指静脉端点的第二数量以及所述第一数量和第二数量的和值；识别模块，用于根据所述第一数量、第二数量以及所述和值，预先保存的每个指静脉图像对应的指静脉交叉点数量、指静脉端点数量以及总数量，确定所述待识别指静脉图像对应的待匹配指静脉图像；验证模块，用于根据所述待匹配指静脉图像，确定所述待识别指静脉图像是否验证通过。
- 根据权利要求6所述的装置，其特征在于，所述识别模块，具体用于将预先保存的指静脉图像中对应的指静脉交叉点数量、指静脉端点数量以及总数量，与所述第一数量、第二数量以及所述和值对应相同的指静脉图像，确定为所述待识别指静脉图像对应的第一待匹配指静脉图像；或，用于将预先保存的指静脉图像中对应的指静脉交叉点数量与所述第一数量相同的指静脉图像确定为所述待识别指静脉图像对应的第二待匹配指静脉图像。
- 根据权利要求7所述的装置，其特征在于，所述识别模块，具体用于将预先保存的指静脉图像中对应的总数量与所述和值的差值在预设的差值阈值范围内的指静脉图像确定为所述待识别指静脉图像对应的第三待匹配指静脉图像；或，用于将预先保存的指静脉图像中对应的总数量与所述和值相同的指静脉图像确定为所述待识别指静脉图像对应的第四待匹配指静脉图像。
- 一种电子设备，其特征在于，所述电子设备至少包括处理器和存储器，所述处理器用于执行存储器中存储的计算机程序时实现根据权利要求1-5中任一所述的基于指静脉图像的认证方法的步骤。
- 一种计算机可读存储介质，其特征在于，其存储有计算机程序，所述计算机程序被处理器执行时实现根据权利要求1-5中任一所述的基于指静脉图像的认证方法的步骤。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2020/129480 WO2022104552A1 (zh) | 2020-11-17 | 2020-11-17 | 一种基于指静脉图像的认证方法、装置、设备和存储介质 |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2020/129480 WO2022104552A1 (zh) | 2020-11-17 | 2020-11-17 | 一种基于指静脉图像的认证方法、装置、设备和存储介质 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2022104552A1 true WO2022104552A1 (zh) | 2022-05-27 |
Family
ID=81707983
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2020/129480 WO2022104552A1 (zh) | 2020-11-17 | 2020-11-17 | 一种基于指静脉图像的认证方法、装置、设备和存储介质 |
Country Status (1)
| Country | Link |
|---|---|
| WO (1) | WO2022104552A1 (zh) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101853378A (zh) * | 2010-05-24 | 2010-10-06 | 哈尔滨工程大学 | 基于相对距离的手指静脉识别方法 |
| CN108319887A (zh) * | 2017-01-18 | 2018-07-24 | 中国移动通信有限公司研究院 | 一种身份认证的方法和系统 |
| JP2019020220A (ja) * | 2017-07-14 | 2019-02-07 | 公益財団法人鉄道総合技術研究所 | 画像処理装置、及び画像処理方法、ならびにプログラム |
| CN109977909A (zh) * | 2019-04-04 | 2019-07-05 | 山东财经大学 | 基于细节点区域匹配的手指静脉识别方法及系统 |
| CN111079551A (zh) * | 2019-11-25 | 2020-04-28 | 五邑大学 | 基于奇异值分解的手指静脉识别方法、装置和存储介质 |
-
2020
- 2020-11-17 WO PCT/CN2020/129480 patent/WO2022104552A1/zh active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101853378A (zh) * | 2010-05-24 | 2010-10-06 | 哈尔滨工程大学 | 基于相对距离的手指静脉识别方法 |
| CN108319887A (zh) * | 2017-01-18 | 2018-07-24 | 中国移动通信有限公司研究院 | 一种身份认证的方法和系统 |
| JP2019020220A (ja) * | 2017-07-14 | 2019-02-07 | 公益財団法人鉄道総合技術研究所 | 画像処理装置、及び画像処理方法、ならびにプログラム |
| CN109977909A (zh) * | 2019-04-04 | 2019-07-05 | 山东财经大学 | 基于细节点区域匹配的手指静脉识别方法及系统 |
| CN111079551A (zh) * | 2019-11-25 | 2020-04-28 | 五邑大学 | 基于奇异值分解的手指静脉识别方法、装置和存储介质 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110287971B (zh) | 数据验证方法、装置、计算机设备及存储介质 | |
| CN110503682B (zh) | 矩形控件识别方法、装置、终端及存储介质 | |
| KR20170016231A (ko) | 사용자 인증을 위한 멀티-모달 퓨전 방법 및 사용자 인증 방법 | |
| CN106663157A (zh) | 用户认证方法、执行该方法的装置及存储该方法的记录介质 | |
| CN101751550B (zh) | 快速指纹搜索方法及快速指纹搜索系统 | |
| US20210201068A1 (en) | Image processing method and apparatus, and electronic device | |
| US20170124380A1 (en) | Fingerprint image processing method and device | |
| US11710342B2 (en) | Fingerprint matching method and apparatus, electronic equipment and readable storage medium | |
| CN113221601A (zh) | 字符识别方法、装置及计算机可读存储介质 | |
| WO2022104552A1 (zh) | 一种基于指静脉图像的认证方法、装置、设备和存储介质 | |
| WO2024051427A1 (zh) | 硬币识别方法、系统及存储介质 | |
| CN111222367B (zh) | 一种指纹识别方法及装置、存储介质、终端 | |
| CN111931672A (zh) | 字迹识别方法、装置、计算机设备及存储介质 | |
| WO2020237481A1 (zh) | 反色区域的确定方法、指纹芯片及电子设备 | |
| KR20230156823A (ko) | 지문 식별 방법, 장치, 전자 장치 및 저장 매체 | |
| TWI775038B (zh) | 字元識別方法、裝置及電腦可讀取存儲介質 | |
| CN112395981B (zh) | 一种基于指静脉图像的认证方法、装置、设备及介质 | |
| JP6927611B1 (ja) | 特徴量抽出装置、特徴量抽出方法、及び、プログラム | |
| CN114529570A (zh) | 图像分割方法、图像识别方法、用户凭证补办方法及系统 | |
| CN111986176B (zh) | 一种裂纹图像识别方法、系统、终端及可读存储介质 | |
| KR100391182B1 (ko) | 직접 골 추적을 이용한 지문 특징 추출방법 | |
| CN113221907A (zh) | 一种车辆部件分割方法、装置、设备及存储介质 | |
| CN114241463A (zh) | 签名验证方法、装置、计算机设备和存储介质 | |
| CN112613016A (zh) | 指纹识别开机方法、装置和计算机 | |
| CN111767916A (zh) | 图像检测方法、装置、设备及存储介质 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20961843 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 20961843 Country of ref document: EP Kind code of ref document: A1 |