CN111488907B - Robust image recognition method based on dense PCANet - Google Patents

Robust image recognition method based on dense PCANet Download PDF

Info

Publication number
CN111488907B
CN111488907B CN202010147376.0A CN202010147376A CN111488907B CN 111488907 B CN111488907 B CN 111488907B CN 202010147376 A CN202010147376 A CN 202010147376A CN 111488907 B CN111488907 B CN 111488907B
Authority
CN
China
Prior art keywords
feature
dense
image
steps
atlas
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
Application number
CN202010147376.0A
Other languages
Chinese (zh)
Other versions
CN111488907A (en
Inventor
李小薪
徐晨雅
胡海根
周乾伟
郝鹏翼
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang University of Technology ZJUT
Original Assignee
Zhejiang University of Technology ZJUT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang University of Technology ZJUT filed Critical Zhejiang University of Technology ZJUT
Priority to CN202010147376.0A priority Critical patent/CN111488907B/en
Publication of CN111488907A publication Critical patent/CN111488907A/en
Application granted granted Critical
Publication of CN111488907B publication Critical patent/CN111488907B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Abstract

A robust image recognition method based on dense PCANet comprises two steps of robust feature extraction and nearest neighbor classification based on chi-square distance. The robust feature extraction process uses dense connection of feature graphs and dense coding of pattern graphs, wherein the dense connection is to combine the features output by all convolution layers to form wider convolution layer features; dense coding, i.e. when using convolutional layers for pattern coding, uses smaller jump amplitudes so that the pattern map reflects as much as possible the correlation between the feature maps. The classification process comprises the following steps: step 1, acquiring distance measurement from an image to be identified to each training image based on chi-square distance in a high-dimensional histogram feature space; and 2, obtaining a class mark corresponding to the training sample with the minimum distance measurement as the class mark of the image to be identified. The method and the device can effectively process the changes such as shielding, illumination change, resolution difference and the like in the image to be identified, thereby effectively improving the identification rate of the offset image.

Description

Robust image recognition method based on dense PCANet
Technical Field
The invention relates to the field of image processing and pattern recognition, in particular to robust image recognition with large difference between an image to be recognized and a training image, which is mainly used for processing and recognizing images in reality.
Background
Recently, in the field of computer vision and image recognition, deep neural networks (Deep Neural Network, DNN), represented by convolutional neural networks (Convolutional Neural Networks, CNN), have met with great success, and on some disclosed data sets, the classification capabilities of leading edge deep learning methods even exceed those of humans, for example: authentication accuracy on LFW face database, image classification accuracy on ImageNet, and handwriting digital recognition accuracy on MNIST, etc. However, in practice, the image to be identified tends to have a large difference in "distribution" or "structure" from the training image, which can cause DNN to suffer from a large-scale recognition error, which phenomenon is called "Covariate Shift" in the field of deep learning.
Disclosure of Invention
In order to overcome the defect of low image recognition rate caused by covariate offset of the existing image recognition method, the invention provides a robust image recognition method based on Dense PCANet (DPCANET). DPCANET can effectively solve the recognition problem caused by covariate offset, and particularly can greatly improve the image recognition performance when the images to be recognized have offset with larger amplitude such as shielding, illumination change, resolution difference and the like.
The technical scheme adopted for solving the technical problems is as follows:
a robust image recognition method based on dense PCANet, comprising the steps of:
step 1 selecting J images A= { A 1 ,…,A J As training set, the corresponding class label is
Figure GDA0004161671420000021
Y＝{Y 1 ,…,Y K The number is the set of images to be identified, i.e. the test set, here +.>
Figure GDA0004161671420000022
Respectively represent the C on the real number domain 0 An image with length and width of m x n of E {1,3} channels;
step 2, initializing parameters and input data: order the
Figure GDA0004161671420000023
Here, a->
Figure GDA00041616714200000226
For indicating the stage at which the network is located,
Figure GDA00041616714200000225
indicating that the network is in training phase->
Figure GDA0004161671420000024
Indicating that the network is in a testing stage; let l=0, where l is used to indicate the number of layers of the input image or feature map in the network,/>
Figure GDA0004161671420000025
Wherein n=j,>
Figure GDA0004161671420000026
let f= { F 1 ,…,F N The symbol "represents a set of feature maps generated by the convolutional layers, where +.>
Figure GDA0004161671420000027
Figure GDA0004161671420000028
Representing an empty set;
step 3 consists of
Figure GDA0004161671420000029
Construction of matrix->
Figure GDA00041616714200000210
Figure GDA00041616714200000211
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure GDA00041616714200000212
Figure GDA00041616714200000213
is->
Figure GDA00041616714200000214
Mean value of->
Figure GDA00041616714200000215
Figure GDA00041616714200000216
Representing from->
Figure GDA00041616714200000217
B e {1,2, …, mn } feature blocks of size k×k extracted from the c-th channel, vec (·) represents the operation of stretching the matrix into column vectors;
step 4 if
Figure GDA00041616714200000218
Indicating that the network is in a testing stage, jumping to the step 7, otherwise, executing the next step;
step 5 calculation
Figure GDA00041616714200000219
Main direction->
Figure GDA00041616714200000220
Wherein (1)>
Figure GDA00041616714200000221
Is covariance matrix->
Figure GDA00041616714200000222
The i' th eigenvector of (a), the corresponding eigenvalue is lambda i′ And->
Figure GDA00041616714200000223
Step 6 from V (l ) Acquisition of C l+1 Individual channel dependent filter bank
Figure GDA00041616714200000224
Step 7 the feature atlas X of the (1) th convolution layer is calculated as follows (l+1) :7.1 Will) be
Figure GDA0004161671420000031
Projected to
Figure GDA0004161671420000032
7.2 Will->
Figure GDA0004161671420000033
The elements in (a) are reorganized into feature atlas +.>
Figure GDA0004161671420000034
Wherein (1)>
Figure GDA0004161671420000035
And is also provided with
Figure GDA0004161671420000036
Figure GDA0004161671420000037
Here, a->
Figure GDA0004161671420000038
Representation->
Figure GDA0004161671420000039
Column vectors from row a to row b of column c, a% b representing a remainder of b, +.>
Figure GDA00041616714200000310
Representation rounding down the real number a, mat m×n (v) represents that an arbitrary column vector is +.>
Figure GDA00041616714200000311
Rearranging into an m×n matrix;
step 8 feature atlas X (l+1) Incorporated in F:
Figure GDA00041616714200000312
step 9, let l=l+1, execute the above steps 3 to 8 until l=l, where L represents a predetermined maximum convolution layer number;
step 10, performing dense coding on the feature atlas F to obtain a mode atlas P: p= { P i, β} i＝1,…,N；β＝1,…,B Wherein, the method comprises the steps of, wherein,
Figure GDA00041616714200000313
beta e {1, …, B } pattern diagram representing the ith sample, F i,· Representing feature map subset F i In>
Figure GDA00041616714200000314
T represents the number of channels participating in the encoding of a single pattern, 1.ltoreq.τ.ltoreq.T, USF (. Cndot.) represents a unit step function (Unit Step Function, USF), and the input value is binarized by comparison with 0, i.e.:
Figure GDA00041616714200000315
step 11 extracts histogram features H from the pattern atlas P: h= [ H ] i ] i＝1,…,N Wherein H is i ＝[H i,1 ,…,H i,B ] T ，H i,β ＝Qhist(P i,β )，Qhist(P i,β ) Representing the pattern diagram P i,β Divided into Q blocks, a histogram is extracted from each block, each histogram using 2 T The number of packets, i.e. the code value of the statistical pattern diagram is 2 for each feature block T The frequency of occurrence in the individual packets;
step 12 if
Figure GDA00041616714200000419
Make H Te =h, jump to step 14; otherwise, let H Tr =h, perform the next step;
step 13 order
Figure GDA0004161671420000041
l＝0，/>
Figure GDA0004161671420000042
Wherein n=k,>
Figure GDA0004161671420000043
executing the steps 3 to 11;
step 14 calculates a metric matrix m= [ M ] i,j ] i＝1,…,J；j＝1,…,K Wherein, the method comprises the steps of, wherein,
Figure GDA0004161671420000044
here the number of the elements is the number,
Figure GDA0004161671420000045
wherein D represents
Figure GDA0004161671420000046
And->
Figure GDA0004161671420000047
Length of->
Figure GDA0004161671420000048
Representation->
Figure GDA0004161671420000049
The d element of (a)>
Figure GDA00041616714200000410
Representation of
Figure GDA00041616714200000411
The d element of (a);
step 15, calculating class id= [ Id ] of each sample in the test set Y i ] i＝1,…,K ：
Figure GDA00041616714200000412
Wherein M is i Represents the ith column vector in the metric matrix M, minIndx (·) represents M i Index of the smallest element in the (c).
Further, in the step 7, the feature atlas X of the (1+1) th convolution layer is calculated as follows (l+1) ：
7.1 Will) be
Figure GDA00041616714200000413
Projection to +.>
Figure GDA00041616714200000414
7.2 Will) be
Figure GDA00041616714200000415
The elements in (a) are reorganized into feature atlas +.>
Figure GDA00041616714200000416
Figure GDA00041616714200000417
Wherein (1)>
Figure GDA00041616714200000418
And is also provided with
Figure GDA0004161671420000051
c＝j％C l+1 The method comprises the steps of carrying out a first treatment on the surface of the Here, a->
Figure GDA0004161671420000052
Representation->
Figure GDA0004161671420000053
Columns from row a to row b of column cThe vector, a% b, represents a to b remainder,
Figure GDA0004161671420000054
representation rounding down the real number a, mat m×n (v) represents that an arbitrary column vector is +.>
Figure GDA0004161671420000055
Rearranged into an mxn matrix.
The technical conception of the invention is as follows: when the images to be identified and the training set images have large offsets such as shielding, illumination change, resolution difference and the like, the identification performance of the existing neural network model is often greatly reduced, and PCANet can better solve the problems. However, PCANet does not fully exploit the learned features: (1) PCANet only uses the feature map output by the last convolution layer to generate subsequent pattern map and histogram features; (2) When the PCANet performs mode encoding, the PCANet uses a large jump, and the correlation between the feature maps cannot be fully utilized. In order to solve the problems, insanenet inspired by the invention, dense connection and dense coding are introduced into a network model of PCANet so as to enrich the extracted features of the PCANet as much as possible, thereby improving the robustness of the PCANet. Dense connection, i.e.: combining all the characteristics output by the convolution layers to form wider convolution layer characteristics; dense coding, i.e.: in pattern coding using convolutional layers, smaller jump amplitudes are used so that the pattern reflects correlation between feature patterns as much as possible.
The beneficial effects of the invention are mainly shown in the following steps: the method can more effectively process the changes such as shielding, illumination change, resolution difference and the like in the image to be identified, thereby effectively improving the identification rate of the offset image.
Drawings
Fig. 1 is a feature map extraction process of dense PCANet according to the present invention, wherein,
Figure GDA0004161671420000056
a convolution operator is represented, and the step 7 of the invention content is detailed; the U-shaped representation performs dense connection on the feature mapA union operator; />
Figure GDA0004161671420000057
The method comprises the following steps of (1) extracting the block histogram characteristics of a pattern diagram, and referring to step 11 of the invention content in detail;
FIG. 2 is a classification process of dense PCANet according to the present invention;
FIG. 3 is a test set and training set sample from an AR face database, where (a) is a test set I sample, (b) is a test set II sample, (c) is a test set III sample, and (d) is a training set sample;
FIG. 4 is a process for extracting feature blocks from a feature map, where (a) is the original feature map, (b) is boundary zero padding, (c) is feature block selection, and (d) is the selected multi-channel feature block;
FIG. 5 (a) is a schematic diagram of the Vec (·) operator stretching the matrix into column vectors, FIG. 5 (b) is mat m×n An (-) operator resets the column vector to a schematic of the matrix;
fig. 6 is a pattern diagram generated by four networks, (a) represents PCANet, (b) represents DPCANet-1, (c) represents DPCANet-2, (d) represents DPCANet-3, where DPCANet-1 represents DPCANet employing only dense linking to the feature diagram, DPCANet-2 represents DPCANet employing only dense encoding to the pattern diagram, and DPCANet-3 represents DPCANet employing both dense linking to the feature diagram and dense encoding to the pattern diagram.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
Referring to fig. 1 to 6, a robust image recognition method based on Dense PCANet (DPCANet), the method comprising the steps of:
step 1 selecting J images A= { A 1 ,…,A J As training set, the corresponding class label is
Figure GDA0004161671420000061
Y＝{Y 1 ,…,Y K The number is the set of images to be identified, i.e. the test set, here +.>
Figure GDA0004161671420000062
Respectively represent the C on the real number domain 0 Image with length width m×n of E {1,3} channels, specifically, C 0 =1 represents a gray scale image, C 0 =3 denotes RGB image, fig. 3 shows a training set sample from AR face database and three sample subsets of images to be identified;
step 2, initializing parameters and input data: order the
Figure GDA0004161671420000071
Here, a->
Figure GDA0004161671420000072
For indicating the stage at which the network is located,
Figure GDA0004161671420000073
indicating that the network is in training phase->
Figure GDA0004161671420000074
Indicating that the network is in a testing stage; let l=0, where l is used to indicate the number of layers of the input image or feature map in the network,/>
Figure GDA0004161671420000075
Wherein n=j,>
Figure GDA0004161671420000076
let f= { F 1 ,…,F N The symbol "represents a set of feature maps generated by the convolutional layers, where +.>
Figure GDA0004161671420000077
Figure GDA0004161671420000078
Representing an empty set;
step 3 consists of
Figure GDA0004161671420000079
ConstructionMatrix->
Figure GDA00041616714200000710
Figure GDA00041616714200000711
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure GDA00041616714200000712
Figure GDA00041616714200000713
is->
Figure GDA00041616714200000714
Mean value of->
Figure GDA00041616714200000715
Figure GDA00041616714200000716
Representing from->
Figure GDA00041616714200000717
B e {1,2, …, mn } feature blocks of size k×k extracted from the c-th lane, vec (·) represents the operation of stretching the matrix into column vectors. Here, the size of the selected feature block, i.e., the size of the learned PCA filter, is typically taken as k=3 or k=5; when selecting the feature blocks, it should be noted that the number of the feature blocks selected in the single feature map on the single channel should be equal to the size m×n of the feature map, in order to achieve this, the feature blocks need to be selected downward and rightward with 1 as an interval, and the boundaries of the feature map need to be filled with 0, as shown in fig. 4 (a) - (b); FIG. 5 (a) gives an example of the operation of the Vec (-) operator;
step 4 if
Figure GDA00041616714200000718
If the network is in the test stage, jumping to the step 7, otherwiseThen, executing the next step;
step 5 calculation
Figure GDA0004161671420000081
Main direction->
Figure GDA0004161671420000082
Wherein (1)>
Figure GDA0004161671420000083
Is covariance matrix->
Figure GDA0004161671420000084
The i' th eigenvector of (a), the corresponding eigenvalue is lambda i′ And->
Figure GDA0004161671420000085
Step 6 from V (l) Acquisition of C l+1 Individual channel dependent filter bank
Figure GDA0004161671420000086
Step 7 the feature atlas X of the (1) th convolution layer is calculated as follows (l+1) :7.1 Will) be
Figure GDA0004161671420000087
Projected to
Figure GDA0004161671420000088
7.2 Will->
Figure GDA0004161671420000089
The elements in (a) are reorganized into feature atlas +.>
Figure GDA00041616714200000810
Wherein (1)>
Figure GDA00041616714200000811
And is also provided with
Figure GDA00041616714200000812
Figure GDA00041616714200000813
Here, a->
Figure GDA00041616714200000814
Representation->
Figure GDA00041616714200000815
Column vectors from row a to row b of column c, a% b representing a remainder of b, +.>
Figure GDA00041616714200000816
Representation rounding down the real number a, mat m×n (v) represents that an arbitrary column vector is +.>
Figure GDA00041616714200000817
Rearranged into an mxn matrix, FIG. 5 (b) shows mat m×n An example of a (-) operation;
step 8 feature atlas X (l+1) Incorporated in F:
Figure GDA00041616714200000818
step 9, let l=l+1, execute the above steps 3 to 8 until l=l, where L represents a predetermined maximum convolution layer number; usually we can take L.epsilon.2, 3;
step 10, performing dense coding on the feature atlas F to obtain a mode atlas P: p= { P i,β } i＝1,…,N；β＝1,…,B Wherein, the method comprises the steps of, wherein,
Figure GDA00041616714200000819
beta e {1, …, B } pattern diagram representing the ith sample, F i,· Representing feature map subset F i In>
Figure GDA00041616714200000820
T represents the number of channels involved in the encoding of a single pattern, typically set t=8, τ(1. Ltoreq.τ.ltoreq.T) for controlling the step size at intervals when the feature map is acquired, typically τ=T/2, USF (·) represents a unit step function (Unit Step Function, USF), and the input value is binarized by comparison with 0, i.e.:
Figure GDA0004161671420000091
step 11 extracts histogram features H from the pattern atlas P: h= [ H ] i ] i＝1,…,N Wherein H is i ＝[H i,1 ,…,H i,B ] T ，H i,β ＝Qhist(P i,β )，Qhist(P i,β ) Representing the pattern diagram P i,β Divided into Q blocks, a histogram is extracted from each block, each histogram using 2 T The number of packets, i.e. the code value of the statistical pattern diagram is 2 for each feature block T The frequency of occurrence in the individual packets;
step 12 if
Figure GDA0004161671420000092
Make H Te =h, jump to step 14; otherwise, let H Tr =h, perform the next step;
step 13 order
Figure GDA0004161671420000093
l＝0，/>
Figure GDA0004161671420000094
Wherein n=k,>
Figure GDA0004161671420000095
executing the steps 3 to 11;
step 14 calculates a metric matrix m= [ M ] i,j ] i＝1,…,J；j＝1,…,K Wherein, the method comprises the steps of, wherein,
Figure GDA0004161671420000096
here the number of the elements is the number,
Figure GDA0004161671420000097
wherein D represents
Figure GDA0004161671420000098
And->
Figure GDA0004161671420000099
Length of->
Figure GDA00041616714200000910
Representation->
Figure GDA00041616714200000911
The d element of (a)>
Figure GDA00041616714200000912
Representation of
Figure GDA00041616714200000913
The d element of (a);
step 15, calculating class id= [ Id ] of each sample in the test set Y i ] i＝1,…,K ：
Figure GDA00041616714200000914
Wherein M is i Represents the ith column vector in the metric matrix M, minIndx (·) represents M i Index of the smallest element in the (c).
Table 1 for the training and test sets given in fig. 3, the recognition rates of three versions of DPCANet (DPCANet-1, DPCANet-2, DPCANet-3) were compared with the existing method (VGG-Face, LCNN, PCANet), as can be seen: DPCANet-1 to DPCANet-3 all show better performance than PCANet, but each of the performance of DPCANet-1 and DPCANet-2 has better or worse, and DPCANet-3 has the optimal recognition performance, especially when the resolution of the image to be recognized is lower, the advantage is more remarkable.
Figure GDA0004161671420000101
Table 1.

Claims (2)

1. A robust image recognition method based on dense PCANet, the method comprising the steps of:
step 1 selecting J images A= { A 1 ,…,A J As training set, the corresponding class label is
Figure FDA0004161671400000011
Y＝{Y 1 ,…,Y K The number is the set of images to be identified, i.e. the test set, here +.>
Figure FDA0004161671400000012
Respectively represent the C on the real number domain 0 An image with length and width of m x n of E {1,3} channels;
step 2, initializing parameters and input data: order the
Figure FDA0004161671400000013
Here, a->
Figure FDA0004161671400000014
For indicating the stage in which the network is located, +.>
Figure FDA0004161671400000015
Indicating that the network is in training phase->
Figure FDA0004161671400000016
Indicating that the network is in a testing stage; let l=0, where l is used to indicate the number of layers of the input image or feature map in the network,/>
Figure FDA0004161671400000017
Wherein n=j,>let f= { F 1 ,…,F N The symbol "represents a set of feature maps generated by the convolutional layers, where +.>
Figure FDA0004161671400000019
Figure FDA00041616714000000110
Representing an empty set;
step 3 consists of
Figure FDA00041616714000000111
Construction of matrix->
Figure FDA00041616714000000112
Figure FDA00041616714000000113
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure FDA00041616714000000114
Figure FDA00041616714000000115
is->
Figure FDA00041616714000000116
Mean value of->
Figure FDA00041616714000000117
Figure FDA00041616714000000118
Representing from->
Figure FDA00041616714000000119
Is the c-th pass of (2)B epsilon {1,2, …, mn } feature blocks of size k×k extracted in the trace, vec (·) represents the operation of stretching the matrix into column vectors;
step 4 if
Figure FDA00041616714000000120
Indicating that the network is in a testing stage, jumping to the step 7, otherwise, executing the steps 5-6;
step 5 calculation
Figure FDA00041616714000000121
Main direction->
Figure FDA00041616714000000122
Wherein (1)>
Figure FDA00041616714000000123
Is covariance matrix->
Figure FDA00041616714000000124
The i' th eigenvector of (a), the corresponding eigenvalue is lambda i′ And->
Figure FDA00041616714000000125
Step 6 from V (l) Acquisition of C l+1 Individual channel dependent filter bank
Figure FDA0004161671400000021
C l+1 ≤k 2 ；
Step 7 computing the feature atlas X of the 1+1th convolution layer (l+1) ；
Step 8 feature atlas X (l+1) Incorporated in F:
Figure FDA0004161671400000022
step 9, let l=l+1, execute the above steps 3 to 8 until l=l, where L represents a predetermined maximum convolution layer number;
step 10, performing dense coding on the feature atlas F to obtain a mode atlas P: p= { P i，β } i＝1，...，N；β＝1，...，B Wherein, the method comprises the steps of, wherein,
Figure FDA0004161671400000023
beta e {1, …, B } pattern diagram representing the ith sample, F i, Representing feature map subset F i In>
Figure FDA0004161671400000024
T represents the number of channels participating in the encoding of a single pattern, τ is the step size of the interval used for controlling the acquisition of the feature map, 1 is less than or equal to τ is less than or equal to T, USF (·) represents a unit step function, and the input value is binarized by comparing with 0, namely:
Figure FDA0004161671400000025
step 11 extracts histogram features H from the pattern atlas P: h= [ H ] i ] i＝1,…,N Wherein H is i ＝[H i,1 ,…,H i,B ] T ，H i,β ＝Qhist(P i,β )，Qhist(P i,β ) Representing the pattern diagram P i,β Divided into Q blocks, a histogram is extracted from each block, each histogram using 2 T The number of packets, i.e. the code value of the statistical pattern diagram is 2 for each feature block T The frequency of occurrence in the individual packets;
step 12 if
Figure FDA0004161671400000026
Make H Te =h, jump to step 14; otherwise, let H Tr =h, perform the next step;
step 13 order
Figure FDA0004161671400000027
l＝0，/>
Figure FDA0004161671400000028
Wherein n=k,>
Figure FDA0004161671400000029
executing the steps 3 to 11;
step 14 calculates a metric matrix m= [ M ] i,j ] i＝1,…,J；j＝1,…,K Wherein, the method comprises the steps of, wherein,
Figure FDA0004161671400000031
here the number of the elements is the number,
Figure FDA0004161671400000032
wherein D represents
Figure FDA0004161671400000033
And->
Figure FDA0004161671400000034
Length of->
Figure FDA0004161671400000035
Representation->
Figure FDA0004161671400000036
The d element of (a)>
Figure FDA0004161671400000037
Representation->
Figure FDA0004161671400000038
The d element of (a);
step 15, calculating class id= [ Id ] of each sample in the test set Y i ] i＝1,…,K ：
Figure FDA0004161671400000039
Wherein M is i Represents the ith column vector in the metric matrix M, minIndx (·) represents M i Index of the smallest element in the (c).
2. The robust image recognition method based on dense PCANet as recited in claim 1, wherein in said step 7, the feature atlas X of the l+1th convolution layer is calculated as follows (l+1) ：
7.1 Will) be
Figure FDA00041616714000000310
Projected to W (l+1) ：/>
Figure FDA00041616714000000311
7.2 Will) be
Figure FDA00041616714000000312
Reorganizing elements in a feature atlas X (l+1) ：/>
Figure FDA00041616714000000313
Wherein, the liquid crystal display device comprises a liquid crystal display device,
Figure FDA00041616714000000314
and is also provided with
Figure FDA00041616714000000315
c＝j％C l+1 The method comprises the steps of carrying out a first treatment on the surface of the Here, a->
Figure FDA00041616714000000316
Representation->
Figure FDA00041616714000000317
Column vectors from rows a to b of column c, a% b representing a-to-b remainder,
Figure FDA00041616714000000318
representation rounding down the real number a, mat m×n (v) represents that an arbitrary column vector is +.>
Figure FDA00041616714000000319
Rearranged into an mxn matrix.
CN202010147376.0A 2020-03-05 2020-03-05 Robust image recognition method based on dense PCANet Active CN111488907B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010147376.0A CN111488907B (en) 2020-03-05 2020-03-05 Robust image recognition method based on dense PCANet

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010147376.0A CN111488907B (en) 2020-03-05 2020-03-05 Robust image recognition method based on dense PCANet

Publications (2)

Publication Number Publication Date
CN111488907A CN111488907A (en) 2020-08-04
CN111488907B true CN111488907B (en) 2023-07-14

Family

ID=71811696

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010147376.0A Active CN111488907B (en) 2020-03-05 2020-03-05 Robust image recognition method based on dense PCANet

Country Status (1)

Country Link
CN (1) CN111488907B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113191411B (en) * 2021-04-22 2023-02-07 杭州卓智力创信息技术有限公司 Electronic sound image file management method based on photo group

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105447473A (en) * 2015-12-14 2016-03-30 江苏大学 PCANet-CNN-based arbitrary attitude facial expression recognition method
CN107194375A (en) * 2017-06-20 2017-09-22 西安电子科技大学 Video sequence sorting technique based on three-dimensional principal component analysis network
CN109410251A (en) * 2018-11-19 2019-03-01 南京邮电大学 Method for tracking target based on dense connection convolutional network

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10713563B2 (en) * 2017-11-27 2020-07-14 Technische Universiteit Eindhoven Object recognition using a convolutional neural network trained by principal component analysis and repeated spectral clustering

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105447473A (en) * 2015-12-14 2016-03-30 江苏大学 PCANet-CNN-based arbitrary attitude facial expression recognition method
CN107194375A (en) * 2017-06-20 2017-09-22 西安电子科技大学 Video sequence sorting technique based on three-dimensional principal component analysis network
CN109410251A (en) * 2018-11-19 2019-03-01 南京邮电大学 Method for tracking target based on dense connection convolutional network

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
Chan, TH；et al.PCANet: A Simple Deep Learning Baseline for Image Classification?.IEEE Transactions on Image Processing.2015,第24卷(第12期),第5017-5032页. *
Zhiwen Huang；et al.Medical Image Classification Using a Light-Weighted Hybrid Neural Network Based on PCANet and DenseNet.IEEE Access.2020,第8卷第24697-24712页. *
张幸蕊.随机采样技术在2D-LDA与PCANet人脸识别算法上的应用研究.信息科技.2020,(第2期),全文. *

Also Published As

Publication number Publication date
CN111488907A (en) 2020-08-04

Similar Documents

Publication Publication Date Title
CN113343707B (en) Scene text recognition method based on robustness characterization learning
CN108416377A (en) Information extracting method in block diagram and device
US10311322B2 (en) Character information recognition method based on image processing
CN108229588B (en) Machine learning identification method based on deep learning
CN102779157B (en) Method and device for searching images
CN109740606A (en) A kind of image-recognizing method and device
CN111488907B (en) Robust image recognition method based on dense PCANet
CN113052859A (en) Super-pixel segmentation method based on self-adaptive seed point density clustering
CN112686104A (en) Deep learning-based multi-vocal music score identification method
CN115908421A (en) Active learning medical image segmentation method based on superpixels and diversity
CN111310820A (en) Foundation meteorological cloud chart classification method based on cross validation depth CNN feature integration
CN106709501B (en) Scene matching area selection and reference image optimization method of image matching system
CN114387454A (en) Self-supervision pre-training method based on region screening module and multi-level comparison
CN109389173B (en) M-CNN-based test paper score automatic statistical analysis method and device
CN115410059B (en) Remote sensing image part supervision change detection method and device based on contrast loss
CN108492345B (en) Data block dividing method based on scale transformation
CN111488906B (en) Low-resolution image recognition method based on channel correlation PCANet
CN111488905B (en) Robust image recognition method based on high-dimensional PCANet
CN106056575A (en) Image matching method based on object similarity recommended algorithm
US9092688B2 (en) Assisted OCR
CN115984639A (en) Intelligent detection method for fatigue state of part
CN111209872B (en) Real-time rolling fingerprint splicing method based on dynamic programming and multi-objective optimization
CN111382703B (en) Finger vein recognition method based on secondary screening and score fusion
CN113887737A (en) Sample set automatic generation method based on machine learning
CN113223098A (en) Preprocessing optimization method for image color classification

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