CN112633226B - Face verification method and system based on quaternion fractional order pseudo Zernike moment - Google Patents
Face verification method and system based on quaternion fractional order pseudo Zernike moment Download PDFInfo
- Publication number
- CN112633226B CN112633226B CN202011622736.4A CN202011622736A CN112633226B CN 112633226 B CN112633226 B CN 112633226B CN 202011622736 A CN202011622736 A CN 202011622736A CN 112633226 B CN112633226 B CN 112633226B
- Authority
- CN
- China
- Prior art keywords
- fractional order
- order pseudo
- zernike moment
- face image
- quaternion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012795 verification Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 28
- 239000011159 matrix material Substances 0.000 claims abstract description 62
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 35
- 230000009466 transformation Effects 0.000 claims abstract description 28
- 238000004364 calculation method Methods 0.000 claims abstract description 22
- 230000001131 transforming effect Effects 0.000 claims abstract description 8
- 238000006243 chemical reaction Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims 1
- 238000012423 maintenance Methods 0.000 description 7
- 238000007726 management method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011840 criminal investigation Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002792 vascular Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Abstract
The application discloses a face verification method based on quaternion fractional order pseudo Zernike moment, which comprises the following steps: collecting a color face image of an identity person to be verified; dividing the color face image into I according to RGB three channels R 、I G 、I B Three images; respectively carrying out fractional order pseudo Zernike moment transformation on the three images to obtain three fractional order pseudo Zernike moment feature matrixes; transforming three fractional order pseudo Zernike moment feature matrixes into a quaternion fractional order pseudo Zernike moment feature matrix by adopting a quaternion fractional order pseudo Zernike moment transformation rapid calculation method, and obtaining an identification feature matrix of the color face image; and matching the recognition feature matrix of the color face image with the recognition feature matrix in the pre-established face image feature library by using a K-NN algorithm to finish the face verification. The color face features extracted by using the quaternion fractional order pseudo Zernike moment have higher robustness, and the verification rate of the face verification model is effectively improved by the fast calculation algorithm.
Description
Technical Field
The application belongs to the field of face recognition, and particularly relates to a face verification method and a face verification system based on quaternion fractional order pseudo Zernike moment, which can be used for login verification and attendance checking of working staff of a rail transit maintenance management system and can be used for rapidly and robustly carrying out face recognition.
Background
Compared with the verification mode of the traditional rail transit maintenance management system, the face verification has better safety, confidentiality and convenience. The face recognition technology starts in 60 s of 20 th century, and has very wide application in the personal authentication and identification field and the criminal investigation field. In recent 20 years, expert scholars propose a plurality of face recognition algorithms, but the existing face recognition algorithms still have the problems of low recognition speed and low algorithm robustness when the illumination conditions are poor and the facial expressions and the gestures are rich. The face recognition technology is divided into two main types, namely key point extraction and feature extraction, and the key point of the face recognition algorithm based on feature extraction is whether the extracted features have stronger robustness and faster calculation speed. The transform domain features have a stronger interference rejection capability than the spatial domain features and a smaller number of transform domain coefficients may carry a larger amount of information. The fractional order transformation is an overall process of orthogonal transformation, which can show the transformation of signals from time domain to frequency domain, and the fractional order transformation not only comprises the frequency domain characteristics of the signals, but also comprises the time domain characteristics of the signals, so that the fractional order transformation has wide application in digital image processing. Color image quaternion representation has been widely used in color image processing in the past two decades to address the effects of lighting condition changes and color on recognition. The proposal of the quaternion representation mode of the color image greatly solves the influence of the illumination condition change and the color on the image recognition algorithm.
Disclosure of Invention
The application aims to provide a face verification method and a face verification system based on quaternion fractional order pseudo Zernike moment, which are used for solving the problems of low feature extraction speed and low robustness of a face verification module for user login and attendance of a traditional rail transit maintenance management system in the prior art.
In order to achieve the above purpose, the application adopts the following technical scheme:
on the other hand, the application provides a face verification method based on quaternion fractional order pseudo Zernike moment, which comprises the following steps:
collecting a color face image of an identity person to be verified;
dividing the color face image into I according to RGB three channels R 、I G 、I B Three images;
will I R 、I G 、I B The three images are respectively subjected to fractional order pseudo Zernike moment transformation to obtain three fractional order pseudo Zernike moment feature matrixes;
transforming the fractional order pseudo Zernike moment characteristic matrix into a quaternion fractional order pseudo Zernike moment characteristic matrix by adopting a quaternion fractional order pseudo Zernike moment transformation rapid calculation method to obtain an identification characteristic matrix of the color face image;
and matching the recognition feature matrix of the color face image with the recognition feature matrix in the pre-established face image feature library by using a K-NN algorithm to finish the face verification.
Further, the construction algorithm of the fractional order pseudo Zernike moments is defined as follows:
for a two-dimensional continuous function f (r, θ) in polar coordinates, the fractional order pseudo Zernike moment is:
wherein α is the fractional order; n and m are non-negative integers, which are the order and the repeatability of the fractional order pseudo Zernike moment respectively; j is an imaginary unit of number,FrPR αn,m (r) is a radial polynomial defined as:
where h is the sum index;
for a gray image f (x, y) of size n×n, the discrete fractional order Zernike moments are defined as:
wherein, frPR αn,m (r) is a radial polynomial, r x,y and θx,y Respectively asThe following formula:
wherein ,
further, the quaternion fractional order pseudo Zernike moment conversion rapid calculation method is obtained through deduction of the relation between the fractional order pseudo Zernike moment and the quaternion fractional order pseudo Zernike moment, and a specific operation formula is as follows:
wherein ,
wherein, frPZM αn,m (fζ), ζ ε { R, G, B } are fractional order pseudo Zernike moments of the red, green, and blue three channels, respectively; re (z) represents the real part of the conventional complex number z, and Im (z) represents the imaginary part of the conventional complex number z; mu is the unit pure quaternion, mu＝ai+bj+ck，i. j and k are imaginary units.
Further, discretization of the fractional order pseudo Zernike moments can be quickly achieved by a radial polynomial defined in the recursive formula (2), the recursive formula of the fractional order pseudo Zernike moments being similar to the Zernike moments, expressed as:
wherein the coefficient K 1 ,K 2 ,K 3 and K4 Given by equation 9:
further, the method for constructing the facial image feature library comprises the following steps:
collecting color face images of each person;
dividing each color face image into I according to RGB three channels R 、I G 、I B Three images;
will I R 、I G 、I B The three images are respectively subjected to fractional order pseudo Zernike moment transformation to obtain three fractional order pseudo Zernike moment feature matrixes;
and transforming the fractional order pseudo Zernike moment characteristic matrix into a quaternion fractional order pseudo Zernike moment characteristic matrix by adopting a quaternion fractional order pseudo Zernike moment transformation rapid calculation method to obtain a recognition characteristic matrix of each color face image, wherein the recognition characteristic matrix of all the color face images form a face image characteristic library.
Further, the matching the recognition feature matrix of the color face image with the recognition feature matrix in the pre-established face image feature library by using a K-NN algorithm comprises the following steps:
and (3) taking K=2 in the K-NN algorithm, finding out 2 nearest neighbor features with Euclidean distance to the recognition feature matrix of the color face image from a face image feature library, and completing face verification by taking the nearest neighbor features except for the nearest neighbor features as recognition results.
On the other hand, the application also provides a face verification system based on the quaternion fractional order pseudo Zernike moment, which comprises the following steps:
the face acquisition unit is configured to acquire a color face image of an identity person to be verified;
an image preprocessing unit configured to divide the color face image into I according to RGB three channels R 、I G 、I B Three images;
a first conversion unit configured to convert I R 、I G 、I B The three images are respectively subjected to fractional order pseudo Zernike moment transformation to obtain three fractional order pseudo Zernike moment feature matrixes;
the second transformation unit is configured to transform the fractional order pseudo Zernike moment characteristic matrix into a quaternion fractional order pseudo Zernike moment characteristic matrix by adopting a quaternion fractional order pseudo Zernike moment transformation rapid calculation method, so as to obtain an identification characteristic matrix of the color face image;
and the feature matching unit is configured to match the recognition feature matrix of the color face image with the recognition feature matrix in the pre-established face image feature library by using a K-NN algorithm to finish face verification.
On the other hand, the application provides a face verification system based on quaternion fractional order pseudo Zernike moment, which comprises a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is used for operating according to the instruction to execute the steps of the face verification method based on the quaternion fractional order pseudo Zernike moment.
In another aspect, the present application provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the aforementioned face verification method based on quaternion fractional order pseudo Zernike moments.
Compared with the prior art, the application has the following advantages and beneficial effects: the application adopts quaternion fractional order pseudo Zernike moment conversion as a feature extraction algorithm, and the extracted face features have rotation scaling robustness; the rapid calculation method can rapidly finish the face verification of the staff of the rail transit maintenance management system, and effectively improves the verification rate of the face verification model.
Drawings
FIG. 1 is a flow chart of a face verification method based on quaternion fractional order pseudo Zernike moments according to an embodiment of the application;
FIG. 2 is a flowchart of an algorithm according to an embodiment of the present application;
FIG. 3 is a graph comparing the fast computation and direct computation run-time of the quaternion fractional order pseudo Zernike moment transform of the present application.
Detailed Description
The application is further described below in connection with specific embodiments. The following examples are only for more clearly illustrating the technical aspects of the present application, and are not intended to limit the scope of the present application.
As shown in fig. 1, the embodiment of the application provides a face verification method based on quaternion fractional order pseudo Zernike moments, which comprises the following steps:
step S11, collecting a color face image of an identity person to be verified;
step S12, dividing the color face image into I according to RGB three channels R 、I G 、I B Three images;
step S13, I R 、I G 、I B The three images are respectively subjected to fractional order pseudo Zernike moment transformation to obtain three fractional order pseudo Zernike moment feature matrixes;
wherein, the construction algorithm of the fractional order pseudo Zernike moment is defined as follows:
for a two-dimensional continuous function f (r, θ) in polar coordinates, the fractional order pseudo Zernike moment is:
wherein α is the fractional order; n and m are non-negative integers, which are the order and the repeatability of the fractional order pseudo Zernike moment respectively; j is an imaginary unit of number,FrPR αn,m (r) is a radial polynomial defined as:
where h is the sum index.
For a gray image f (x, y) of size n×n, the discrete fractional order Zernike moments are defined as:
wherein, frPR αn,m (r) is a radial polynomial, r x,y and θx,y The following formulas are respectively shown:
wherein ,
s14, transforming the fractional order pseudo Zernike moment characteristic matrix into a quaternion fractional order pseudo Zernike moment characteristic matrix by adopting a quaternion fractional order pseudo Zernike moment conversion rapid calculation method to obtain an identification characteristic matrix of the color face image;
the quaternion fractional order pseudo Zernike moment conversion rapid calculation method is obtained through deduction of the relation between the fractional order pseudo Zernike moment and the quaternion fractional order pseudo Zernike moment, and a specific operation formula is as follows:
wherein, frPZM αn,m (f ξ ) ζ ε { R, G, B }, is the fractional order pseudo Zernike moment of the red, green, blue three channels, respectively; re (z) represents the real part of the conventional complex number z, and Im (z) represents the imaginary part of the conventional complex number z; μ is a unit pure quaternion, μ=ai+bj+ck.i. j and k are imaginary units.
The relationship given in equation 7 allows us to quickly implement the discretization of the quaternion fractional order pseudo Zernike moments using fractional order pseudo Zernike moments. Discretization of the fractional order pseudo Zernike moments can also be achieved quickly by a recursive algorithm whose key idea is the radial polynomials defined in recursive calculation 2. The recursive formula of the fractional order pseudo Zernike moments is similar to the Zernike moments, expressed as:
wherein the coefficient K 1 ,K 2 ,K 3 and K4 Given by equation 8:
and S15, matching the recognition feature matrix of the color face image with the recognition feature matrix in the pre-established face image feature library by using a K-NN algorithm to finish face verification.
In the step, K=2 in a K-NN algorithm is taken, 2 nearest neighbor features with Euclidean distance to an identification feature matrix of the color face image are found out from a face image feature library, other nearest neighbor features except the nearest neighbor features are identification results, namely two color images with the most similar quaternion fractional order pseudo Zernike moment features are removed, and finally face verification is completed.
Further, the method for constructing the facial image feature library comprises the following steps:
collecting color face images of each person;
dividing each color face image into I according to RGB three channels R 、I G 、I B Three images;
will I R 、I G 、I B The three images are respectively subjected to fractional order pseudo Zernike moment transformation to obtain three fractional order pseudo Zernike moment feature matrixes;
and transforming the fractional order pseudo Zernike moment characteristic matrix into a quaternion fractional order pseudo Zernike moment characteristic matrix by adopting a pre-deduced quaternion fractional order pseudo Zernike moment conversion rapid calculation method to obtain a recognition characteristic matrix of each color face image, wherein the recognition characteristic matrix of all the color face images form a face image characteristic library.
As shown in fig. 2, an algorithm flow chart of an embodiment of the present application, taking a rail transit maintenance management system as an example, includes the following steps:
step 21, collecting a color face image I of each worker, then carrying out quick quaternion fractional order pseudo Zernike moment conversion on the collected color face image I, and establishing a face recognition data model of the worker in a maintenance management system, wherein the specific steps are as follows:
step 211, dividing the color face image I into I according to RGB three channels R 、I G 、I B Three images;
and 212, performing fractional order pseudo Zernike moment transformation on the images on the RGB three channels respectively to obtain three fractional order pseudo Zernike moment characteristic matrixes.
And 213, transforming the three fractional order pseudo Zernike moment feature matrixes into a quaternion fractional order pseudo Zernike moment feature matrix by a quaternion fractional order pseudo Zernike moment transformation rapid calculation method, and finally obtaining the identification feature matrix of the color face image I.
Step 214, the recognition feature matrix of each color face image I is stored in the face image storage unit, and a face image feature library is obtained.
Step 22, collecting a face image I of a work staff to be authenticated in an authentication mode 1 ；
Step 23, adopting face recognition algorithm to collect face image I 1 The verification is carried out, and the specific steps are as follows:
step 231, face image I 1 Obtaining face image I by using quick quaternion fractional order pseudo Zernike moment conversion 1 Is a recognition feature matrix E of the (a);
step 232, using K-NN algorithm to image the face I 1 Matching the recognition feature matrix E with the recognition feature matrix in the face image feature library of the staff, taking K=2 in the K-NN algorithm, finding out 2 nearest neighbor features of the Euclidean distance of the feature matrix, and removing other nearest neighbor features outside the feature matrix as recognition results, namely two color images with the most similar quaternion fractional order pseudo Zernike moment features, so as to finally finish face verification of the staff of the vascular system.
The quick calculation algorithm fully considers the correlation among quaternions when calculating the fractional order quaternion pseudo Zernike moment and uses a recursion method to quickly calculate, thereby solving the problem of high direct calculation complexity of the quaternion pseudo Zernike moment. In order to better demonstrate the proposed fast calculation effect, a comparison experiment is performed between the proposed fractional order quaternion pseudo Zernike moment fast calculation algorithm and a direct algorithm, and the experimental result is shown in FIG. 3. Fig. 3 shows the run time of 80 pictures 768 x 1024 using two different algorithms, as is evident from the figure: the algorithm provided by the application has higher calculation speed, and experimental results show that the algorithm provided by the application has strong superiority in calculation efficiency.
The embodiment of the application can be seen that the color face features extracted by using the quaternion fractional order pseudo Zernike moment have higher robustness, the proposed rapid calculation algorithm has higher calculation speed, the face verification of the staff of the rail transit maintenance management system can be completed rapidly, and the verification rate of the face verification model is improved effectively.
In another embodiment, the present application further provides a face verification system based on quaternion fractional order pseudo Zernike moments, including:
the face acquisition unit is configured to acquire a color face image of an identity person to be verified;
an image preprocessing unit configured to divide the color face image into I according to RGB three channels R 、I G 、I B Three images;
a first conversion unit configured to convert I R 、I G 、I B The three images are respectively subjected to fractional order pseudo Zernike moment transformation to obtain three fractional order pseudo Zernike moment feature matrixes;
the second transformation unit is configured to transform the fractional order pseudo Zernike moment characteristic matrix into a quaternion fractional order pseudo Zernike moment characteristic matrix by adopting a quaternion fractional order pseudo Zernike moment transformation rapid calculation method, so as to obtain an identification characteristic matrix of the color face image;
and the feature matching unit is configured to match the recognition feature matrix of the color face image with the recognition feature matrix in the pre-established face image feature library by using a K-NN algorithm to finish face verification.
Further, the face verification system further includes: and the face image storage unit is configured to store the identification feature matrix of each color face image so as to obtain a face image feature library.
In another embodiment, the application provides a face verification system based on quaternion fractional order pseudo Zernike moments, which comprises a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is used for operating according to the instruction to execute the steps of the face verification method based on the quaternion fractional order pseudo Zernike moment.
In another embodiment, the application provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the steps of the aforementioned quaternion fractional order pseudo Zernike moment based face verification method.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application 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, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing is merely a preferred embodiment of the present application, and it should be noted that modifications and variations could be made by those skilled in the art without departing from the technical principles of the present application, and such modifications and variations should also be regarded as being within the scope of the application.
Claims (9)
1. The face verification method based on the quaternion fractional order pseudo Zernike moment is characterized by comprising the following steps of:
collecting a color face image of an identity person to be verified;
dividing the color face image into I according to RGB three channels R 、I G 、I B Three images;
will I R 、I G 、I B The three images are respectively subjected to fractional order pseudo Zernike moment transformation to obtain three fractional order pseudo Zernike moment feature matrixes;
transforming the fractional order pseudo Zernike moment characteristic matrix into a quaternion fractional order pseudo Zernike moment characteristic matrix by adopting a quaternion fractional order pseudo Zernike moment transformation rapid calculation method to obtain an identification characteristic matrix of the color face image;
and matching the recognition feature matrix of the color face image with the recognition feature matrix in the pre-established face image feature library by using a K-NN algorithm to finish the face verification.
2. The method of claim 1, wherein the construction algorithm of the fractional order pseudo Zernike moments is defined as follows:
for a two-dimensional continuous function f (r, θ) in polar coordinates, the fractional order pseudo Zernike moment is:
wherein α is the fractional order; n and m are non-negative integers, which are the order and the repeatability of the fractional order pseudo Zernike moment respectively; j is an imaginary unit of number,FrPR αn,m (r) is a radial polynomial defined as:
where h is the sum index;
for a gray image f (x, y) of size n×n, the discrete fractional order Zernike moments are defined as:
wherein, frPR αn,m (r) is a radial polynomial, r x,y and θx,y The following formulas are respectively shown:
wherein ,
3. the method according to claim 2, wherein the quaternion fractional order pseudo Zernike moment transformation fast calculation method is derived from a relationship between fractional order pseudo Zernike moments and quaternion fractional order pseudo Zernike moments, and the specific operation formula is as follows:
wherein ,
wherein, frPZM αn,m (f ξ ) ζ ε { R, G, B }, is the fractional order pseudo Zernike moment of the red, green, blue three channels, respectively; re (z) represents the real part of the conventional complex number z, and Im (z) represents the imaginary part of the conventional complex number z; μ is a unit pure quaternion, μ=ai+bj+ck,i. j and k are imaginary units, and Ω is an integration region.
4. The method according to claim 2, characterized in that the discretization of the fractional order pseudo Zernike moments is fast achieved by a radial polynomial defined in recursion (2), the recursive formula of the fractional order pseudo Zernike moments being expressed as:
wherein the coefficient K 1 ,K 2 ,K 3 and K4 Given by formula (9):
5. the method according to claim 1, wherein the method for constructing the face image feature library comprises:
collecting color face images of each person;
dividing each color face image into I according to RGB three channels R 、I G 、I B Three images;
will I R 、I G 、I B The three images are respectively subjected to fractional order pseudo Zernike moment transformation to obtain three fractional order pseudo Zernike moment feature matrixes;
and transforming the fractional order pseudo Zernike moment characteristic matrix into a quaternion fractional order pseudo Zernike moment characteristic matrix by adopting a pre-deduced quaternion fractional order pseudo Zernike moment conversion rapid calculation method to obtain a recognition characteristic matrix of each color face image, wherein the recognition characteristic matrix of all the color face images form a face image characteristic library.
6. The method of claim 1, wherein the matching the recognition feature matrix of the color face image with the recognition feature matrix in the pre-established face image feature library using a K-NN algorithm comprises:
and (3) taking K=2 in the K-NN algorithm, finding out 2 nearest neighbor features with Euclidean distance to the recognition feature matrix of the color face image from a face image feature library, and completing face verification by taking the nearest neighbor features except for the nearest neighbor features as recognition results.
7. A face verification system based on quaternion fractional order pseudo Zernike moments, comprising:
the face acquisition unit is configured to acquire a color face image of an identity person to be verified;
an image preprocessing unit configured to divide the color face image into I according to RGB three channels R 、I G 、I B Three images;
a first conversion unit configured to convert I R 、I G 、I B The three images are respectively subjected to fractional order pseudo Zernike moment transformation to obtain three fractional order pseudo Zernike moment feature matrixes;
the second transformation unit is configured to transform the fractional order pseudo Zernike moment characteristic matrix into a quaternion fractional order pseudo Zernike moment characteristic matrix by adopting a quaternion fractional order pseudo Zernike moment transformation rapid calculation method, so as to obtain an identification characteristic matrix of the color face image;
and the feature matching unit is configured to match the recognition feature matrix of the color face image with the recognition feature matrix in the pre-established face image feature library by using a K-NN algorithm to finish face verification.
8. The human face verification system based on the quaternion fractional order pseudo Zernike moment is characterized by comprising a processor and a storage medium;
the storage medium is used for storing instructions;
the processor being operative according to the instructions to perform the steps of the method according to any one of claims 1 to 6.
9. Computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011622736.4A CN112633226B (en) | 2020-12-30 | 2020-12-30 | Face verification method and system based on quaternion fractional order pseudo Zernike moment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011622736.4A CN112633226B (en) | 2020-12-30 | 2020-12-30 | Face verification method and system based on quaternion fractional order pseudo Zernike moment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112633226A CN112633226A (en) | 2021-04-09 |
| CN112633226B true CN112633226B (en) | 2023-09-22 |
Family
ID=75287363
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011622736.4A Active CN112633226B (en) | 2020-12-30 | 2020-12-30 | Face verification method and system based on quaternion fractional order pseudo Zernike moment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112633226B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484432A (en) * | 2014-12-20 | 2015-04-01 | 辽宁师范大学 | Color image searching method based on quaternion exponential moment |
| CN110390307A (en) * | 2019-07-25 | 2019-10-29 | 首都师范大学 | Expression recognition method, Expression Recognition model training method and device |
| CN110610144A (en) * | 2019-08-28 | 2019-12-24 | 首都师范大学 | Expression recognition method and system for privacy protection |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150023558A1 (en) * | 2012-03-30 | 2015-01-22 | Muhittin Gokmen | System and method for face detection and recognition using locally evaluated zernike and similar moments |
-
2020
- 2020-12-30 CN CN202011622736.4A patent/CN112633226B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484432A (en) * | 2014-12-20 | 2015-04-01 | 辽宁师范大学 | Color image searching method based on quaternion exponential moment |
| CN110390307A (en) * | 2019-07-25 | 2019-10-29 | 首都师范大学 | Expression recognition method, Expression Recognition model training method and device |
| CN110610144A (en) * | 2019-08-28 | 2019-12-24 | 首都师范大学 | Expression recognition method and system for privacy protection |
Non-Patent Citations (1)
| Title |
|---|
| 基于伪Zernike矩归一化的人脸特征提取方法;杨迪等;计算机工程与应用(35);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112633226A (en) | 2021-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021227349A1 (en) | Front-end facial image encryption and recognition method for biometric privacy protection | |
| Yang et al. | Fvras-net: An embedded finger-vein recognition and antispoofing system using a unified cnn | |
| Bodla et al. | Deep heterogeneous feature fusion for template-based face recognition | |
| Han et al. | Multispectral palmprint recognition using wavelet-based image fusion | |
| Jagadeesan et al. | Cryptographic key generation from multiple biometric modalities: Fusing minutiae with iris feature | |
| CN102111418A (en) | Facial feature cryptographic key generation-based internet identity authentication method | |
| CN109190535A (en) | A kind of face blee analysis method and system based on deep learning | |
| CN113537008B (en) | Micro expression recognition method based on self-adaptive motion amplification and convolutional neural network | |
| Gu et al. | Latent fingerprint registration via matching densely sampled points | |
| CN104077742A (en) | GABOR characteristic based face sketch synthetic method and system | |
| El-Abed et al. | Quality assessment of image-based biometric information | |
| CN112633226B (en) | Face verification method and system based on quaternion fractional order pseudo Zernike moment | |
| Yin et al. | Dynamic difference learning with spatio-temporal correlation for deepfake video detection | |
| Balakumar et al. | Secure biometric key generation scheme for cryptography using combined biometric features of fingerprint and iris | |
| Cao et al. | Gaze-aided eye detection via appearance learning | |
| Luong et al. | Reconstructing a fragmented face from a cryptographic identification protocol | |
| Yu et al. | Multispectral palmprint recognition using score-level fusion | |
| Qu et al. | Image sequence facial expression recognition based on deep residual network | |
| Khadilkar et al. | Face identification based on discrete wavelet transform and neural networks | |
| Canavan et al. | Face recognition by multi-frame fusion of rotating heads in videos | |
| Mohite et al. | Thermal and Visual Face Recognition using Eigenfaces and Transfer Learning | |
| Pantopoulou et al. | An fpga-implemented parallel system of face recognition, for digital forensics applications | |
| Sindhu et al. | Fingerprint authentication based on adaptive greedy registration of minutiae pairs | |
| Plata et al. | How to save your face: a facial recognition method robust against image reconstruction | |
| Zhu et al. | A Joint Cascaded Framework for Simultaneous Eye State, Eye Center, and Gaze Estimation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |