CN115527242A

CN115527242A - Identity recognition method and device, electronic equipment and storage medium

Info

Publication number: CN115527242A
Application number: CN202211216045.3A
Authority: CN
Inventors: 支天波; 张小晶; 林荣荣; 梁志明
Original assignee: Guizhou Xiaoai Robot Technology Co ltd
Current assignee: Guizhou Xiaoai Robot Technology Co ltd
Priority date: 2022-09-30
Filing date: 2022-09-30
Publication date: 2022-12-27

Abstract

The invention discloses an identity recognition method, an identity recognition device, electronic equipment and a storage medium. The method comprises the following steps: gabor filtering is carried out on finger biological characteristics of the identified user under multiple scales and multiple directions to obtain multiple Gabor filtering images; determining a single-scale Gabor filtering image corresponding to each scale according to Gabor filtering images in multiple directions respectively corresponding to each scale; generating a multi-scale combined Gabor filtering image according to each single-scale Gabor filtering image; and according to the multi-scale combined Gabor filtering image, carrying out identity recognition on the recognition user. By executing the technical scheme, the accuracy of identifying the biological characteristics of the finger of the user can be improved, redundant information in the filtering image is effectively reduced, the operation time is saved, the occupied space is saved, and the requirement of the user on the high performance of identity authentication is better met.

Description

Identity recognition method and device, electronic equipment and storage medium

Technical Field

The present invention relates to the field of code recognition technologies, and in particular, to an identity recognition method and apparatus, an electronic device, and a storage medium.

Background

Biometric identification is a technology for automatically identifying identity by using unique physiological and behavioral characteristics of a human body, and is widely applied to access of security systems such as entrance guard, attendance and government affairs, digital terminals and identity authentication of network access. Finger-based biometric recognition can utilize various biometric characteristic combinations, and has performance advantages in noise resistance, universality, large data recognition time efficiency and the like compared with other biometric recognition, and has recently become a research hotspot.

In the prior art, the finger biological characteristics are identified by means of optical technology, silicon technology, ultrasonic technology and the like by mainly utilizing the characteristics of different patterns, breakpoints and worse points of human fingerprints and utilizing the characteristics of characteristic pickup, verification and identification technology.

In the process of implementing the invention, the inventor finds that the prior art has the following defects: the performance of finger biological feature recognition is sensitive to illumination change and finger gesture usually, and the prior art is easily disturbed, and the reliability is not high, and the prior art needs to collect more lines characteristics of human fingerprint, produces redundancy easily on the information, has occupied great storage space, has also increased the operation time of discernment.

Disclosure of Invention

The invention provides an identity recognition method, an identity recognition device, electronic equipment and a storage medium, and provides a finger biological characteristic recognition technology which gives consideration to recognition speed and storage space.

In a first aspect, an embodiment of the present invention provides an identity identification method, where the method includes:

gabor filtering is carried out on finger biological characteristics of the identified user under multiple scales and multiple directions to obtain multiple Gabor filtering images;

selecting a single-scale Gabor filtering image corresponding to each scale from Gabor filtering images in multiple directions corresponding to each scale;

generating a multi-scale combined Gabor filtering image according to each single-scale Gabor filtering image;

and according to the multi-scale combined Gabor filtering image, carrying out identity recognition on the recognition user.

In a second aspect, an embodiment of the present invention provides an identity recognition apparatus, where the apparatus includes:

the Gabor filtering module is used for carrying out Gabor filtering on the finger biological characteristics of the identified user in multiple scales and multiple directions to obtain multiple Gabor filtering images;

the Gabor filtering image selecting module is used for selecting a single-scale Gabor filtering image corresponding to each scale from Gabor filtering images in a plurality of directions respectively corresponding to each scale;

the Gabor filtering image generating module is used for generating a multi-scale combined Gabor filtering image according to each single-scale Gabor filtering image;

and the identity recognition module is used for carrying out identity recognition on the recognition user according to the multi-scale combined Gabor filtering image.

In a third aspect, an embodiment of the present invention provides an electronic device, where the electronic device includes:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the method of identification according to any of the embodiments of the invention.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where computer instructions are stored, and the computer instructions are configured to, when executed, cause a processor to implement the identity identification method according to any embodiment of the present invention.

According to the technical scheme of the embodiment of the invention, after the finger biological characteristics of the user are identified and the Gabor images are obtained by Gabor filtering in multiple scales and multiple directions, only one single-scale Gabor filtering image is reserved for each scale, and then a pair of multi-scale combined Gabor filtering images is obtained on the basis of the single-scale Gabor filtering images for identifying the identity of the user.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a flowchart of an identity recognition method according to an embodiment of the present invention;

fig. 2 is a flowchart of an identity recognition method according to a second embodiment of the present invention;

fig. 3 is a schematic structural diagram of an identification apparatus according to a third embodiment of the present invention;

fig. 4 is a schematic structural diagram of an electronic device that can be used to implement the fourth embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, shall fall within the protection scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example one

Fig. 1 is a flowchart of an identity recognition method provided in an embodiment of the present invention, where the embodiment is applicable to a case where finger biometric features are used to perform automatic identity authentication, and the method may be executed by an identity recognition device, where the identity recognition device may be implemented in a form of hardware and/or software, and the identity recognition device may be configured in an identity recognition terminal with an identity recognition function, such as a fingerprint lock, an attendance card punch, or a door access. As shown in fig. 1, the method includes:

and S110, carrying out Gabor filtering on the finger biological characteristics of the identified user in multiple scales and multiple directions to obtain multiple Gabor filtering images.

Wherein the finger biometric may include: fingerprint characteristics, texture characteristics on the inner side of a finger joint, texture characteristics on the outer side of the finger joint, texture characteristics on the inner side and the outer side of the root of the finger, finger vein characteristics and the like.

Specifically, the finger biological characteristics of the user can be extracted and identified through a finger biological characteristic extraction module in the identity identification terminal.

The Gabor filter has many applications in the aspects of feature extraction, texture analysis, stereo disparity estimation and the like in image processing, and further, the expression of the Gabor filter is as follows:

wherein j is ² ＝-1，

Mu is a direction factor, v is a scale factor, sigma is a standard deviation of a Gaussian function, j represents an imaginary unit,

taking angles corresponding to the direction factors at different times;

for frequencies, k, corresponding to different scale factors _max Representing the maximum frequency, f is the spacing factor of the kernel function in frequency.

Correspondingly, a plurality of Gabor filtering expressions can be constructed and obtained by setting different direction factors and different scale factors, and then filtering processing is carried out on the finger biological characteristics by using the Gabor filter expressions, so that a plurality of Gabor filtering images can be obtained.

In a specific example, if 8 scales and 8 directions are selected to be set, a total of 64 Gabor filtering expressions can be constructed, and 64 Gabor filtering images can be obtained.

Further, the Gabor filtered image is an image with texture features, which is obtained by processing Gabor filtering through a convolution algorithm.

And S120, determining a single-scale Gabor filtering image corresponding to each scale according to the Gabor filtering images in the multiple directions respectively corresponding to each scale.

As described above, after acquiring a plurality of Gabor filtered images in multiple scales and multiple directions, a multi-direction Gabor filtered image in each dimension may be acquired with each scale as a dimension. In the previous example, after 8 scales and 8 directions of Gabor filtering are performed, 8 Gabor filtered images corresponding to 8 directions are provided at each scale.

In the embodiment, in consideration of the fact that a plurality of Gabor filtering images under each scale are directly used for subsequent identity recognition processing, great redundant information is introduced, further, the subsequent calculation time consumption and the occupation amount of a memory space are greatly increased, on the basis, the creative proposal is that only Gabor filtering images in one direction are reserved in multi-direction Gabor filtering images under each dimension for subsequent processing, and further, the introduction of redundant information can be greatly reduced.

It can be understood that, when the Gabor filtering is performed, it is equivalent to performing convolution with the finger biometric features by using a Gabor filter, and then, each pixel point in the obtained Gabor filtered image has a Gabor response value.

Correspondingly, in an optional implementation manner of this embodiment, determining the single-scale Gabor filtered image corresponding to each scale according to the Gabor filtered images in multiple directions respectively corresponding to each scale may include:

and respectively calculating the sum of Gabor response values of all pixel points in all target Gabor filtering images aiming at the target Gabor filtering images in multiple directions corresponding to the target scale, selecting the target Gabor filtering image with the maximum Gabor response value, and determining the target Gabor filtering image as the single-scale Gabor filtering image corresponding to the target scale.

In another optional implementation manner of this embodiment, determining a single-scale Gabor filtered image corresponding to each scale according to Gabor filtered images in multiple directions respectively corresponding to each scale may further include:

and selecting each pixel point with the maximum Gabor response value from the Gabor filtering images in multiple directions respectively corresponding to each scale, and fusing to obtain a single-scale Gabor filtering image corresponding to each scale.

In the previous example, after the Gabor filtered images in 8 directions corresponding to each scale are processed, only one single-scale Gabor filtered image is obtained. If the total size is 8, 8 single-size Gabor filtering images are obtained correspondingly.

In this alternative embodiment, the concept of "winner is king" in competitive coding is introduced, and it is considered that one single-scale Gabor filter image corresponding to the target scale is generated according to N target Gabor filter images in N directions under the target scale. That is, each pixel point in the single-scale Gabor filter image has N candidate values corresponding to pixel points at the same position in the N target Gabor filter images, and then, a pixel point with the largest response value can be selected from the pixel points at the same position in the N target Gabor filter images to serve as a pixel point of the single-scale Gabor filter image, so that the single-scale Gabor filter image is finally obtained through fusion.

In other words, selecting a Gabor filtered image having a maximum Gabor response value among Gabor filtered images in a plurality of directions respectively corresponding to each scale may include:

after Gabor filtering of K channels in any scale is carried out, and after all pixel points of the K channels are obtained, the pixel points corresponding to the maximum response values in the K Gabor filtering values in the K channels are selected respectively, and a single-scale Gabor filtering image in the scale can be obtained through fusion. The information integrity is guaranteed, and meanwhile, the occupied storage and redundant information are reduced.

And S130, generating a multi-scale combined Gabor filtering image according to each single-scale Gabor filtering image.

In an optional implementation manner of this embodiment, generating a multi-scale combined Gabor filtered image according to each single-scale Gabor filtered image may include:

and carrying out image feature fusion on each single-scale Gabor filtering image to generate a multi-scale combined Gabor filtering image.

The image features are integrated into a technology that image data collected by multiple channels and related to the same target are subjected to image processing, computer technology and the like, favorable information in respective channels is extracted to the maximum extent, and finally high-quality images are synthesized, so that the utilization rate of image information is improved, the interpretation precision and reliability of a computer are improved, and the spatial resolution and the spectral resolution of an original image are improved.

Further, the image feature fusion method adopted by the invention may include: the linear weighting method, the multi-resolution fusion algorithm, the wavelet transform method, etc. are not limited in this embodiment.

As mentioned above, after 8 single-scale Gabor filtered images are obtained, the 8 Gabor filtered images may be finally merged into one Gabor filtered image, and the merged image includes information of the Gabor filtered image with the maximum Gabor response value in the multi-scale multi-direction.

And S140, according to the multi-scale combined Gabor filtering image, carrying out identity recognition on the recognition user.

The identity recognition of the recognized user according to the multi-scale combined Gabor filtering image may include:

carrying out feature coding on the multi-scale combined Gabor filtering image in the multiple directions, and combining feature coding results in the multiple directions to obtain a Gabor feature coding image; generating an image feature vector according to the Gabor feature coding image; and according to the image feature vector, performing identity recognition on the recognition user.

Generating an image feature vector according to the Gabor feature encoded image may include:

dividing the Gabor feature encoded image into a plurality of non-overlapping image sub-blocks; calculating image sub-block feature vectors respectively corresponding to each image sub-block according to the gray value of each pixel point in each image sub-block; and according to the dividing sequence of the image subblocks, serially connecting the image subblock feature vectors of the image subblocks to obtain the image feature vectors.

Wherein, according to the grey scale value of each pixel point in each image sub-block, calculate the image sub-block eigenvector that corresponds respectively with each image sub-block, include:

acquiring a target image sub-block which is processed currently, and generating a gray level sub-image corresponding to the target image sub-block;

counting the occurrence frequency of different gray values according to the gray value of each pixel point in the gray subgraph;

and sequentially arranging the gray values and the occurrence frequencies respectively corresponding to the gray values according to the sequence of the gray values from large to small to obtain the image sub-block feature vectors corresponding to the target image sub-blocks.

The identifying the identity of the identified user according to the image feature vector may include:

inquiring a pre-constructed identity feature library according to the image feature vector, wherein the identity feature library stores a mapping relation between an identity and the identity feature vector;

and acquiring an identity identifier corresponding to the identity feature vector successfully matched with the image feature vector in the identity feature library, wherein the identity identifier is used as an identity identification result of the identified user.

It can be understood that, in the existing technical solution, multi-directional coding is performed on each Gabor filtered image in different directions, but the solution provided in this embodiment is to fuse the Gabor filtered images in different directions into one filtered image by selecting a maximum response value, and then perform multi-directional coding. The embodiment utilizes the neighborhood characteristics in multiple directions, effectively considers the local texture information of the image and eliminates redundant information in the encoding process. Therefore, the recognition accuracy of the improved coding scheme should be better than the original coding scheme in theory. In addition, compared with the original coding scheme, the dimensionality of the feature vectors extracted by the improved scheme is greatly reduced, the operation time can be saved, and less storage space is occupied.

Exemplarily, on the basis of the database Data-1, the identification result of the same identification user finger as that of the present embodiment is encoded by the prior art scheme, and the identification result is shown in table 1: the method for calculating the equal error rate comprises the following steps: taking the False Rejection (FR) as the vertical axis intercept of the DET (Detection error rate map) graph, taking the False Acceptance (FA) as the horizontal axis intercept of the DET graph to make a corresponding DET graph, and the equal error rate of a certain point is the value of the intersection point of the characteristic function of the point and the DET graph. Wherein the single time is the total time required for one identification of the same identified user by a certain scheme.

TABLE 1

Recognition performance	Prior art solutions	Scheme of the embodiment
			Equal error rate	0.20	0.15
Single time of day	0.023	0.010

As shown in the experimental results, the equal error rate of the feature coding scheme of the embodiment is reduced from 0.20% to 0.15% in the prior art scheme, and the feature extraction time of a single finger vein image is also reduced from 0.023s to 0.010s. Compared with the prior art, the scheme has the advantages that the finger biological characteristics are identified more quickly and accurately, and the identification efficiency is improved.

The technical scheme provided by the embodiment of the invention provides an identity recognition method, which comprises the steps of carrying out Gabor filtering on finger biological characteristics of a recognition user under multiple scales and multiple directions to obtain Gabor images under multiple directions to obtain single-scale Gabor filtering images corresponding to each scale, obtaining a multi-scale combined Gabor filtering image on the basis of the single-scale Gabor filtering images, and carrying out identity recognition on the recognition user by utilizing the image. The method solves the problems that the prior art is easily influenced by environmental factors, information redundancy is easily generated, the occupied storage space is large, and identification is slow, realizes faster and more accurate identification of finger biological characteristics, and improves the efficiency of identity identification.

Example two

Fig. 2 is a flowchart of an identity recognition method according to a second embodiment of the present invention, which is a refinement of the steps of the first embodiment. As shown in fig. 2, the method includes:

s210, gabor filtering is carried out on the finger biological characteristics of the identified user under multiple scales and multiple directions, and multiple Gabor filtering images are obtained.

And S220, selecting a single-scale Gabor filtering image corresponding to each scale from the Gabor filtering images in the multiple directions respectively corresponding to each scale.

And S230, generating a multi-scale combined Gabor filtering image according to each single-scale Gabor filtering image.

S240, carrying out feature coding in the multiple directions according to the multi-scale combined Gabor filtering image, and combining the feature coding results in the multiple directions to obtain a Gabor feature coding image.

Specifically, the scale values of the multi-scale combined Gabor filter image are arranged according to the size of the angle, the gray values of the pixel points at the same position in the image are compared, the scale direction of the characteristic image of the angle corresponding to the maximum gray value is used as the direction characteristic of the pixel point, and encoding is performed.

For example, in this embodiment, different directions such as 0 °,22.5 °,45 °,67.5 °,90 °,112.5 ° are selected for feature coding, where 0 ° is coded as 0, 22.5 ° is coded as 1, 45 ° is coded as 2, 67.5 ° is coded as 3, 90 ° is coded as 4, 112.5 ° is coded as 5, and if a pixel point at a same position on a certain finger single-mode directional feature image has the maximum gray value on the 45 ° directional feature image, the pixel point is coded as 2 in the finger single-mode Gabor directional feature coded image, thereby forming the finger three-mode Gabor directional feature coded images in the multiple directions.

And S250, dividing the Gabor feature coded image into a plurality of non-overlapping image sub-blocks.

Specifically, according to the size of the Gabor feature encoded image, the Gabor feature encoded image may be divided into N equal parts in the horizontal direction and M equal parts in the vertical direction, so as to obtain N × M non-overlapping image sub-blocks.

And S260, acquiring the currently processed target image sub-block and generating a gray sub-image corresponding to the target image sub-block.

The gray level subgraph is a gray level graph corresponding to a currently processed target image sub-module; the grayscale map is an image represented by grayscale values (typically 256 levels). The gray scale indicates that an object is represented by black, and an image is displayed by black having different saturation levels, using black as a reference color.

And S270, counting the occurrence frequency of different gray values according to the gray value of each pixel point in the gray subgraph.

Specifically, the method may first calculate all gray values included in the gray sub-image according to the gray value of each pixel point in the gray sub-image, then calculate the occurrence frequency of each gray value in the gray sub-image, and then divide the occurrence frequency by the total number of pixel points in the gray sub-image, thereby obtaining the occurrence frequency of different gray values in the gray sub-image.

S280, sequentially arranging the gray values and the occurrence frequencies respectively corresponding to the gray values according to the sequence of the gray values from large to small to obtain the image sub-block feature vectors corresponding to the target image sub-blocks.

In a specific example, in the gray map of the target image sub-block, the occurrence frequencies of different gray values in the order from large gray value to small gray value include: 253,30 percent; 200,30 percent; 165,30 percent; 23,10 percent.

After the sorting result is obtained, binary coding can be performed on the numerical values according to a preset binary coding mode to obtain a corresponding binary digit sequence and an image subblock feature vector corresponding to the target image subblock.

And S290, according to the dividing sequence of the image subblocks, serially connecting the image subblock feature vectors of the image subblocks to obtain the image feature vectors.

In a specific example, if the Gabor feature coded image is divided into image sub-blocks 1, 2, 3 and 4 according to the dividing order of the image sub-blocks, after obtaining an image sub-block feature vector X1 corresponding to the image sub-block 1, an image sub-block feature vector X2 corresponding to the image sub-block 2, an image sub-block feature vector X3 corresponding to the image sub-block 3 and an image sub-block feature vector X4 corresponding to the image sub-block 4, the image sub-block feature vectors may be concatenated to obtain the image feature vectors (X1, X2, X3, X4).

S2100, inquiring a pre-constructed identity feature library according to the image feature vector, wherein the identity feature library stores a mapping relation between identity marks and identity feature vectors.

In this embodiment, the relationship between the elements may not be one-to-one mapped, for example, the identity feature vector may correspond to a fingerprint biological characteristic having the image vector feature in two identity feature libraries. Further, when the identity feature vector is mapped with at least one identity, the identification is successful.

And S2110, acquiring an identity identifier corresponding to the identity feature vector successfully matched with the image feature vector in the identity feature library, and using the identity identifier as an identity identification result of the identified user.

The technical scheme provided by the embodiment of the invention provides an identity recognition method, wherein a single-scale Gabor filtering image corresponding to each scale is obtained by carrying out Gabor filtering on finger biological features of a recognition user under multiple scales and multiple directions to obtain Gabor images under multiple directions, the target image is processed into target image sub-blocks to generate gray level sub-images corresponding to the target image sub-blocks, an image feature vector is obtained by processing the gray level image, and the image feature vector is utilized to carry out identity recognition on the recognition user. The method solves the problems of easy generation of information redundancy, large occupied storage space and slow identification in the prior art, realizes quicker and more accurate identification of finger biological characteristics, and improves the efficiency of identity identification.

EXAMPLE III

Fig. 3 is a schematic structural diagram of an identity recognition apparatus according to a third embodiment of the present invention. As shown in fig. 3, the apparatus includes a Gabor filtering module 310, a Gabor filtering image selecting module 320, a Gabor filtering image generating module 330, and an identity recognizing module 340, wherein:

a Gabor filtering module 310, configured to perform Gabor filtering on the finger biometric features of the identified user at multiple scales and multiple directions to obtain multiple Gabor filtered images;

a Gabor filtering image selecting module 320, configured to determine, according to Gabor filtering images in multiple directions respectively corresponding to each scale, a single-scale Gabor filtering image corresponding to each scale;

a Gabor filtering image generating module 330, configured to generate a multi-scale combined Gabor filtering image according to each single-scale Gabor filtering image;

and the identity recognition module 340 is configured to perform identity recognition on the recognized user according to the multi-scale combined Gabor filtered image.

According to the technical scheme of the embodiment of the invention, after the finger biological characteristics of the user are identified and the Gabor images are obtained by Gabor filtering in multiple scales and multiple directions, only one single-scale Gabor filtering image is reserved for each scale, and then a set of multi-scale combined Gabor filtering images is obtained on the basis of each single-scale Gabor filtering image to identify the identity of the user.

On the basis of the foregoing embodiments, the Gabor filtered image selecting module 320 may be specifically configured to:

On the basis of the foregoing embodiments, the Gabor filtered image generating module 330 may be specifically configured to:

On the basis of the foregoing embodiments, the identity module 340 may specifically include:

the Gabor feature coding image combination unit is used for carrying out feature coding on the multi-scale combined Gabor filtering image in the multiple directions and combining feature coding results in the multiple directions to obtain a Gabor feature coding image;

the image feature vector generating unit is used for generating an image feature vector according to the Gabor feature coding image;

and the user identity recognition unit is used for carrying out identity recognition on the recognized user according to the image feature vector.

On the basis of the foregoing embodiments, the image feature vector generating unit may specifically include:

an image subblock dividing subunit, configured to divide the Gabor feature encoded image into a plurality of non-overlapping image subblocks;

the image subblock feature vector calculating subunit is used for calculating image subblock feature vectors respectively corresponding to each image subblock according to the gray value of each pixel point in each image subblock;

and the image subblock characteristic vector serial subunit is used for serially connecting the image subblock characteristic vectors of the image subblocks according to the dividing sequence of the image subblocks to obtain the image characteristic vector.

On the basis of the foregoing embodiments, the image sub-block feature vector calculation subunit may be specifically configured to:

On the basis of the foregoing embodiments, the user identification unit may be specifically configured to:

The identity recognition device provided by the embodiment of the invention can execute the identity recognition method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.

Example four

FIG. 4 shows a schematic block diagram of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 4, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 may also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

Processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. The processor 11 performs the various methods and processes described above, for example implementing an identification method as described in embodiments of the invention.

Namely: gabor filtering is carried out on the finger biological characteristics of the identified user under multiple scales and multiple directions to obtain multiple Gabor filtering images;

determining a single-scale Gabor filtering image corresponding to each scale according to Gabor filtering images in multiple directions respectively corresponding to each scale;

In some embodiments, the identification method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the identification method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured in any other suitable manner (e.g., by means of firmware) to perform the identification method described in the embodiments of the present invention.

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the Internet.

The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.

The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An identity recognition method, comprising:

2. The method according to claim 1, wherein determining the single-scale Gabor filtering image corresponding to each scale according to the Gabor filtering images in the plurality of directions respectively corresponding to each scale comprises:

3. The method of claim 1, wherein generating a multi-scale combined Gabor filtered image from each single-scale Gabor filtered image comprises:

4. The method according to any one of claims 1-3, wherein identifying the identified user according to the multi-scale combined Gabor filtered image comprises:

carrying out feature coding on the multi-scale combined Gabor filtering image in the multiple directions, and combining the feature coding results in the multiple directions to obtain a Gabor feature coding image;

generating an image feature vector according to the Gabor feature coding image;

and according to the image feature vector, carrying out identity recognition on the recognition user.

5. The method of claim 4, wherein generating an image feature vector according to the Gabor feature encoded image comprises:

dividing the Gabor feature encoded image into a plurality of non-overlapping image sub-blocks;

calculating image sub-block characteristic vectors respectively corresponding to each image sub-block according to the gray value of each pixel point in each image sub-block;

and according to the dividing sequence of the image subblocks, serially connecting the image subblock feature vectors of the image subblocks to obtain the image feature vectors.

6. The method of claim 5, wherein calculating the image sub-block feature vectors corresponding to each image sub-block according to the gray values of the pixels in each image sub-block comprises:

7. The method of claim 4, wherein identifying the identified user according to the image feature vector comprises:

inquiring a pre-constructed identity feature library according to the image feature vector, wherein the identity feature library stores a mapping relation between an identity mark and the identity feature vector;

8. An identification device, comprising:

the Gabor filtering image selecting module is used for determining a single-scale Gabor filtering image corresponding to each scale according to Gabor filtering images in multiple directions respectively corresponding to each scale;

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the identification method of any one of claims 1-7.

10. A computer-readable storage medium storing computer instructions for causing a processor to perform the method of any one of claims 1-7 when executed.