CN115131588A - Image robust clustering method based on fuzzy clustering - Google Patents
Image robust clustering method based on fuzzy clustering Download PDFInfo
- Publication number
- CN115131588A CN115131588A CN202210665911.0A CN202210665911A CN115131588A CN 115131588 A CN115131588 A CN 115131588A CN 202210665911 A CN202210665911 A CN 202210665911A CN 115131588 A CN115131588 A CN 115131588A
- Authority
- CN
- China
- Prior art keywords
- clustering
- sample
- image
- data
- noise
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 239000011159 matrix material Substances 0.000 claims abstract description 36
- 238000005457 optimization Methods 0.000 claims abstract description 21
- 230000001629 suppression Effects 0.000 claims description 15
- 238000012216 screening Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 18
- 230000000694 effects Effects 0.000 description 4
- 238000010606 normalization Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Computational Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Data Mining & Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to an image robust clustering method based on fuzzy clustering, which screens out images polluted by noise while clustering image data, retains pure and pollution-free image data and has higher robustness to noise change. The invention is an unsupervised algorithm, does not need to use the label data, and reduces a large amount of time for acquiring the label data. The algorithm does not need to update the graph matrix in the solving process, so the calculation complexity of the algorithm is reduced, and the calculation speed is accelerated. Therefore, the fast, effective and robust clustering of the noise-polluted images can be realized. According to the method, the corresponding regularization parameter of each sample can be calculated in a self-adaptive manner through the regularization parameter of the iterative optimization objective function, so that the difficulty in adjusting the regularization parameter is greatly reduced in the application process, the labor cost is saved, and the image clustering accuracy is improved while the image data polluted by noise is robustly screened out.
Description
Technical Field
The invention belongs to the field of image identification and classification and pattern identification, and relates to an image robust clustering method based on fuzzy clustering.
Background
With the development of computer technology and digital imaging systems, it is more and more convenient for people to transmit information through images. However, in a real environment, image information is easily polluted by noise, so that image quality is lost to a certain extent, and effective identification of an image is difficult. Because the processed image information is increasingly complex and the acquisition difficulty of the label is more and more high, the application of the unsupervised image clustering technology in the information era is widely concerned, the image clustering technology can cluster the images in the image database according to the similarity of the images, so that the similarity of the images in the same cluster is as large as possible, and the similarity between different clusters is as small as possible. And the image information is susceptible to noise, and if the images polluted by the noise are still subjected to traditional unsupervised image clustering, the accuracy and reliability of image retrieval are greatly influenced. And screening out the images polluted by noise, and comparing the new images with the clusters with higher similarity in the database one by one to quickly finish the identification and classification. Therefore, the clustering after noise suppression of the image data before the image retrieval can effectively and quickly realize the high-quality image data retrieval.
Likang et al (fuzzy spectral clustering algorithm for hyperspectral image classification) (Chinese scientific and technological paper 2021,16(07): 743-. However, updating the graph matrix also increases the time complexity of the fuzzy clustering algorithm, and affects the operation speed. Although the graph learning and the fuzzy clustering learning are integrated into a combined learning frame, the method is limited by the traditional fuzzy clustering algorithm, the robustness is poor, the noise data cannot be effectively removed, and the subsequent image data retrieval is influenced.
Disclosure of Invention
Technical problem to be solved
In order to avoid the defects of the prior art, the invention provides an image robust clustering method based on fuzzy clustering, which aims at solving the problems that the existing supervised image algorithm needs to consume a large amount of time to obtain a data label, and the influence of noise on image data retrieval and poor robustness cannot be effectively solved.
Technical scheme
An image robust clustering method based on fuzzy clustering is characterized by comprising the following steps:
step 1: for n pictures of u × v resolution, stretching each picture to obtain a 1 × d row vector, where d is u × v; converting image data formed by n pictures into a target data matrix
Wherein each row of the matrix
Represents an image; each image represents a data sample; giving the real category number c contained in the target data, and randomly initializing the clustering centers of the c clusters, namely obtaining the initial
Is the centroid of the jth cluster;
and 2, step: establishing robust fuzzy clustering RFCM framework for noise suppression
Wherein
Is fuzzy membership degree, and the centroid matrix of the cluster is
The matrix Y represents each element Y ij Representing the membership degree of the ith sample belonging to the jth cluster;
for screening n-k noise numbersAccording to s i Is the value of the ith element;
and step 3: alternative iteration optimization robust fuzzy clustering RFCM framework
The solving steps are as follows:
step 3.1: randomly initializing the clustering centers of c clusters to obtain initial clusters
Initializing all elements in Y to Y ij 1/c; definition e i To a sample x with a certain degree of membership i Weighting and summing the resulting values to all cluster center distances, e i Arranged as e in descending order 1 ≤e 2 ≤...≤e k ≤...≤e n Calculating to obtain its correspondence s i ；
Step 3.2: respectively carrying out different optimization on real samples and noise data to obtain Y
S corresponding to the first k samples nearest to all the cluster centers i 1, s for the remaining samples i 0; will be compared with the sequence e i Corresponding sample x i Sorting to obtain sorted data matrix
Its corresponding sorted membership degree matrix
Step 3.2.1: when the sample corresponds to s i When the number of the clusters is 1, q clusters nearest to the real sample are thinned out, and y is limited i L of 0 Norm q, defined
Ith real sample point
Quadratic distance to jth cluster center, RFCM framework equivalent transformation
Calculating an optimal parameter gamma by the parameter gamma in the target function in a self-adaptive mode;
optimizing to obtain the optimal membership degree corresponding to the selected real sample
i∈{1,2,...,k}
Step 3.2.2: for the noise data in the optimization process, s is corresponding to the sample i When the value is equal to 0, the optimal membership value corresponding to the noise data in the optimization process is obtained by solving the Cauchy inequality as
Obtaining the optimal solution of all sample point membership degrees
Is composed of
Step 3.3: fixing s and Y to get a sub-problem of the RFCM framework
Solving the partial derivative of m to be equal to 0 to obtain:
in each optimization process, m, Y and s are continuously updated, and the next iterative operation is carried out again until m is not changed; one row of sample data corresponds to one picture, and according to the obtained membership matrix Y, the label of the cluster corresponding to the maximum value of each row of the sample data is selected as the class of the picture to be divided, so that a predicted label vector is obtained, and image clustering cluster division is realized; the obtained s vector contains k 1, n-k 0 s, and s corresponding to the ith image i If 0, then the picture is screened as a noise contaminated image.
Advantageous effects
According to the image robust clustering method based on fuzzy clustering provided by the invention, the image data is clustered, and simultaneously, the image polluted by noise is screened out, so that pure and pollution-free image data is reserved, and the image robust clustering method based on fuzzy clustering has higher robustness to noise change. The invention is an unsupervised algorithm, does not need to use the label data, and reduces a large amount of time for acquiring the label data. The algorithm does not need to update the graph matrix in the solving process, so the calculation complexity of the algorithm is reduced, and the calculation speed is accelerated. Therefore, the fast, effective and robust clustering of the noise-polluted images can be realized.
The invention provides a noise suppression image clustering method based on an improved robust fuzzy clustering framework of FCM (fuzzy C-means), which can robustly screen out image data polluted by noise in the application process, can also be used for image clustering, simultaneously improves the robustness and precision of an algorithm, and improves the data processing speed by sparsifying a membership matrix. In the algorithm, an objective function is composed of a robust noise suppression term and a regularization term, and self-adaptive weight is added to each sample point through iterative optimization of the objective function, so that pure samples and noise pollution samples are screened, and the robustness of the algorithm is enhanced. And the data samples polluted by noise can be screened by optimizing the objective function, and then the image clustering of noise suppression is carried out.
The method of the invention has the following beneficial effects:
(1) a robust fuzzy clustering algorithm is provided, in the algorithm, a robust noise suppression term of an objective function enables the algorithm to iteratively optimize the objective function, self-adaptive weight is added to each sample point, pure samples and noise pollution samples are screened according to the self-adaptive weight, and the robustness of the algorithm is enhanced.
(2) According to the noise suppression image clustering method based on robust fuzzy clustering provided by the invention, the membership degree matrix is thinned while the robust noise suppression is carried out, so that a more effective sample and characteristic distribution structure is obtained, the influence of noise pollution on image data clustering is avoided, the storage capacity of data is reduced, the calculation amount of the data is reduced, and the calculation efficiency is improved.
(3) The method can adaptively calculate the corresponding regularization parameter of each sample by iteratively optimizing the regularization parameter of the target function, greatly reduce the difficulty of adjusting the regularization parameter in the application process, save the labor cost, and improve the image clustering accuracy while robustly screening the image data polluted by noise.
Drawings
FIG. 1: is a flow chart of the method
FIG. 2 is a schematic diagram: is an example of a partially noisy contaminated image
FIG. 3: is a graph of the results of the detection of the method on a particular data set
Detailed Description
The invention will now be further described with reference to the following examples and drawings:
the invention is realized by the following technical scheme, and the noise suppression image clustering method based on robust fuzzy clustering comprises the following specific steps:
step 1: obtaining image data information to construct a data matrix
For n picture data of u × v resolution, each picture is elongated to obtain a 1 × d pictureA row vector, where d ═ u × v; converting image data formed by n pictures into a target data matrix
Wherein each row of the matrix
Represents an image; each image represents a data sample; giving the real category number c contained in the target data, and randomly initializing the clustering centers of c clusters to obtain the initial
Is the centroid of the jth cluster.
Step 2: establishing a Robust Fuzzy Clustering (RFCM) framework that can perform noise suppression
A Fuzzy C-means (Fuzzy C-means) algorithm is called FCM algorithm for short, and in order to improve the noise suppression robustness of the Fuzzy C-means algorithm, a noise suppression term and a regularization term are introduced into a framework.
Wherein
Is fuzzy membership degree, and the centroid matrix of the cluster is
The matrix Y represents each element Y ij Representing the degree of membership that the ith sample belongs to the jth cluster.
For screening n-k noisy data, s i Is the value of the ith element of s.
And step 3: alternately iteratively optimizing an objective function:
solving three variables of m, Y and s in the objective function by adopting an alternating iterative optimization method, firstly initializing m and Y, and calculating according to a formula to obtain s; fixing s and m, and respectively carrying out different optimizations on the real sample and the noise data to obtain Y; then fixing s and Y, solving m according to a formula, and sequentially circulating until convergence;
the solving steps are as follows:
step 3.1: according to the cluster centers of c clusters which are randomly initialized, obtaining the initial
Initializing all elements in Y to Y ij 1/c. The initial probability of distributing samples to each class is considered to be equal. Definition e i To the sample x with a certain degree of membership i The distances to all cluster centers are weighted and the resulting values are summed. E is to be i Arranged as e in descending order 1 ≤e 2 ≤...≤e k ≤…≤e n The corresponding s can be calculated i
Step 3.2: and respectively carrying out different optimizations on the real sample and the noise data to obtain Y.
In step 3.1 we obtain s corresponding to the first k samples nearest to all cluster centers i 1, s for the remaining samples i 0. E is to be i Sorting according to the sequence from small to large, and sorting the corresponding samples x i Sorting is carried out, and a sorted data matrix can be obtained
Its corresponding sorted membership degree matrix
Step 3.2.1: for real samples. When the sample corresponds to s i When the number of the clusters is 1, only q clusters nearest to the real sample are considered, the membership matrix is thinned, and y is limited i L of 0 The norm is q. Definition of
For the selected ith real sample point
The square of the distance to the jth cluster center, the problem translates equivalently to
The parameter γ in the objective function usually needs to be adjusted appropriately to avoid the occurrence of trivial solution, and the present invention can adaptively calculate the optimal parameter γ.
Optimizing to obtain the optimal membership degree corresponding to the selected real sample
i∈{1,2,...,k}
Step 3.2.2: for noisy data in the optimization process. When the sample corresponds to s i When the value is equal to 0, solving the Cauchy inequality to obtain the optimal membership value corresponding to the noise data in the optimization process
The optimal solution of all sample point membership degrees can be obtained
Is composed of
Step 3.3:
solving the partial derivative of m to be equal to 0 by the subproblem of the objective function to obtain
And finally, after the m, the Y and the s are updated, next iteration operation is carried out again until the m is not changed any more. And one row of sample data corresponds to one picture, and according to the obtained membership matrix Y, the label of the cluster corresponding to the maximum value of each row of the sample data is selected as the class of the picture to be divided, so that a predicted label vector is obtained, and the image clustering cluster division is realized. The obtained s vector contains k 1, n-k 0 s, and s corresponding to the ith image i If 0, then the picture is screened as a noise contaminated image.
The specific embodiment is as follows:
the comprehensive model solving process of the noise suppression image clustering method based on robust fuzzy clustering is shown in figure 1, an ORL face image data set is selected for clustering, the ORL face image data set comprises 400 face images in total, the resolution ratio is 92 multiplied by 112, each face image corresponds to one sample, and the real label corresponding to 400 images is
The predicted labels of 400 images obtained by the clustering algorithm are
Wherein the real label z t And the method is only used for final clustering effect verification and is not included in the clustering algorithm. To test the algorithm, the number of noise contaminated image samples p is 160, for example, with a 40% proportion of noise added. The specific implementation mode comprises the following steps:
step one, inputting an ORL data matrix
The true class number c, the number p of the noise-contaminated image samples is 160 and the membership degree thinning parameter q, wherein each row of the matrix
For one sample, n-400 is the number of samples, d-92 × 112-10304 is the dimension of the data matrix, and c-40 is the number of true categories included in the face data.
And randomly initializing the clustering centers of the c clusters, namely obtaining the initial m. Initializing all elements in Y to Y ij 1/40, and 240, n-p. The initial probability of distributing samples to each class is considered to be equal. I.e., m and Y can be fixed and s can be calculated. Fixing m and Y, converting the objective function into
Definition e i To the sample x with a certain degree of membership i The distances to all cluster centers are weighted and the resulting values are summed.
E is to be i Arranged as e in descending order 1 ≤e 2 ≤...≤e k ≤…≤e n The optimal solution of the objective function can be calculated and obtained in a constraint s T S corresponding to 1-k i
Therefore, the sample data which is not polluted by the noise and the sample which is polluted by the noise can be obtained by screening, and the optimization is continuously carried out in the subsequent iteration process.
Step two: and respectively carrying out different optimizations on the real sample and the noise data to obtain Y.
Obtaining s corresponding to the first k samples nearest to all cluster centers in the first step i 1, s for the remaining samples i 0. E is to be i Sorting according to the sequence from small to large, and sorting the corresponding samples x i Sorting is carried out to obtain a sorted data matrix
Its corresponding sorted membership degree matrix
Step 2.1: for real samples. Definition of
Is a sorted data matrix
The vector composed of the ith row elements.
Is a matrix of degree of membership after sorting
The jth element of row i. When the sample corresponds to s i When 1, a sub-problem of the objective function is
Only q clusters nearest to the real sample are considered, the membership matrix is thinned, and y is limited i L of 0 The norm is q. Definition of
For the selected ith real sample point
Average distance to jth cluster centerThe problem can be equivalently transformed into
The second term of the original objective function is the regularization term to avoid the trivial solution of two extreme cases: the similarity of all samples is 1/n with the similarity of only the nearest neighbor sample being 1. By lagrange multiplier method, KKT conditions and constraints
Since each term of the problem is independent for i, we can be directed to each
Independently solving, solving the objective function equivalence sub-problem by adopting a Lagrange multiplier method, and optimizing to obtain the optimal membership degree corresponding to the selected real sample
i∈{1,2,...,k}
Step 2.2: for noisy data in the optimization process. When the sample corresponds to s i When the value is equal to 0, the optimal membership value corresponding to the noise data in the optimization process is obtained by solving the Cauchy inequality as
The optimal solution of all sample point membership degrees can be obtained
Is composed of
Step three: fix s and Y, solve for m
The objective function sub-problem is then rewritten as
Solving the partial derivative of m to be equal to 0 by the subproblem of the objective function to obtain
And when s, Y and m are updated, next iteration operation is carried out again until the clustering center m is not updated, namely the change of the clustering center m is smaller than a certain threshold value. Contaminated sample correspondence s i When the solution is finished, optimizing the obtained s i The ith sample corresponding to 0 is screened as the image sample polluted by noise, and 160 image samples polluted by noise can be screened out in total. Clustering prediction label capable of directly obtaining 400 face images
So as to achieve considerable clustering effect. Different from classification, the prediction labels obtained by the clustering method can only achieve the grouping effect under the unsupervised condition, so that the numbers in the prediction labels correspond to the real class labels one by one, but the specific corresponding relation cannot be known, and the unsupervised and grouped face data images can be grouped and classified for the face data images without label information, so as to assist face retrieval and greatly improve retrieval precision and speed. By contrasting the real labels z t And a predictive label z obtained by a clustering algorithm p And calculating the accuracy of image clustering.
Take an ORL face image data set (400 pictures, each picture having 92 × 112 pixels) as an example. When 40% of noise is added, the clustering accuracy of the FCM on the ORL face image data is only 8.61%, and the clustering normalization mutual information is 14.13%. When 40% of noise is added, the clustering accuracy of the robust fuzzy clustering-based noise suppression image cluster (RFCM) on the ORL face image data set is 64.83%, the clustering normalization mutual information is 71.29%, 56.22% and 57.16% are respectively improved, and the clustering accuracy of the face image data is remarkably improved.
Claims (1)
1. An image robust clustering method based on fuzzy clustering is characterized by comprising the following steps:
step 1: for n pictures with u × v resolution, lengthening each picture to obtain a 1 × d row vector, where d is u × v; converting image data formed by n pictures into a target data matrix
Wherein each row of the matrix
Represents an image; each image represents a data sample; giving the real category number c contained in the target data, and randomly initializing the clustering centers of the c clusters, namely obtaining the initial
Is the centroid of the jth cluster;
step 2: establishing robust fuzzy clustering RFCM framework for noise suppression
Wherein
Is fuzzy membership degree, and the centroid matrix of the cluster is
The matrix Y represents each element Y ij Representing the membership degree of the ith sample belonging to the jth cluster;
for screening n-k noisy data, s i Is the value of the ith element;
and step 3: alternative iteration optimization robust fuzzy clustering RFCM framework
The solving steps are as follows:
step 3.1: randomly initializing the clustering centers of c clusters to obtain initial clusters
Initializing all elements in Y to Y ij 1/c; definition e i To the sample x with a certain degree of membership i Distances to all cluster centers are weighted and the resulting values are summed, e i Arranged as e in descending order 1 ≤e 2 ≤...≤e k ≤...≤e n Calculating to obtain its correspondence s i ；
Step 3.2: respectively carrying out different optimizations on the real sample and the noise data to obtain Y
S corresponding to the first k samples nearest to all the cluster centers i 1, s for the remaining samples i 0; will be compared with the sequence e i Corresponding sample x i Sorting is carried out to obtain a sorted data matrix
Its corresponding sorted membership degree matrix
Step 3.2.1: when the sample corresponds to s i When the number of the clusters is 1, q clusters nearest to the real sample are thinned out, and y is limited i L of 0 Norm q, defined
Ith real sample point
RFCM framework equivalence transformation to the square of the distance to the jth cluster center
Calculating an optimal parameter gamma by the parameter gamma in the target function in a self-adaptive mode;
optimizing to obtain the optimal membership degree corresponding to the selected real sample
Step 3.2.2: for the noise data in the optimization process, s corresponding to the sample i When the value is equal to 0, the optimal membership value corresponding to the noise data in the optimization process is obtained by solving the Cauchy inequality as
Obtaining the optimal solution of all sample point membership degrees
Is composed of
Step 3.3: fixing s and Y to get a sub-problem of the RFCM framework
Solving the partial derivative of m to be equal to 0 to obtain:
in each optimization process, m, Y and s are continuously updated, and the next iterative operation is carried out again until m is not changed; one row of sample data corresponds to one picture, and according to the obtained membership degree matrix Y, the label of the cluster corresponding to the maximum value of each row of the sample data is selected as the classified class of the picture, so that a predicted label vector is obtained, and the image clustering cluster division is realized; the obtained s vector contains k 1, n-k 0 s, and s corresponding to the ith image i Then the picture is screened as an image contaminated with noise.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210665911.0A CN115131588B (en) | 2022-06-13 | 2022-06-13 | Image robust clustering method based on fuzzy clustering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210665911.0A CN115131588B (en) | 2022-06-13 | 2022-06-13 | Image robust clustering method based on fuzzy clustering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115131588A true CN115131588A (en) | 2022-09-30 |
| CN115131588B CN115131588B (en) | 2024-02-23 |
Family
ID=83377270
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210665911.0A Active CN115131588B (en) | 2022-06-13 | 2022-06-13 | Image robust clustering method based on fuzzy clustering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115131588B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101866522B1 (en) * | 2016-12-16 | 2018-06-12 | 인천대학교 산학협력단 | Object clustering method for image segmentation |
| CN110211126A (en) * | 2019-06-12 | 2019-09-06 | 西安邮电大学 | Image partition method based on intuitionistic fuzzy C mean cluster |
| WO2021007744A1 (en) * | 2019-07-15 | 2021-01-21 | 广东工业大学 | Kernel fuzzy c-means fast clustering algorithm with integrated spatial constraints |
| CN113538445A (en) * | 2021-07-30 | 2021-10-22 | 安徽工业大学 | Image segmentation method and system based on weighted robust FCM clustering |
-
2022
- 2022-06-13 CN CN202210665911.0A patent/CN115131588B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101866522B1 (en) * | 2016-12-16 | 2018-06-12 | 인천대학교 산학협력단 | Object clustering method for image segmentation |
| CN110211126A (en) * | 2019-06-12 | 2019-09-06 | 西安邮电大学 | Image partition method based on intuitionistic fuzzy C mean cluster |
| WO2021007744A1 (en) * | 2019-07-15 | 2021-01-21 | 广东工业大学 | Kernel fuzzy c-means fast clustering algorithm with integrated spatial constraints |
| CN113538445A (en) * | 2021-07-30 | 2021-10-22 | 安徽工业大学 | Image segmentation method and system based on weighted robust FCM clustering |
Non-Patent Citations (1)
| Title |
|---|
| 吴成茂;吴其平;: "一种基于改进PFCM的鲁棒图像分割算法", 西安邮电大学学报, no. 05, 10 September 2017 (2017-09-10) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115131588B (en) | 2024-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106203523B (en) | The hyperspectral image classification method of the semi-supervised algorithm fusion of decision tree is promoted based on gradient | |
| CN111860236B (en) | Small sample remote sensing target detection method and system based on transfer learning | |
| CN109977994B (en) | Representative image selection method based on multi-example active learning | |
| CN113313164B (en) | Digital pathological image classification method and system based on super-pixel segmentation and graph convolution | |
| CN109033978B (en) | Error correction strategy-based CNN-SVM hybrid model gesture recognition method | |
| CN112101430A (en) | Anchor frame generation method for image target detection processing and lightweight target detection method | |
| CN109376787B (en) | Manifold learning network and computer vision image set classification method based on manifold learning network | |
| CN109145964B (en) | Method and system for realizing image color clustering | |
| CN111239137B (en) | Grain quality detection method based on transfer learning and adaptive deep convolution neural network | |
| CN113298009B (en) | Entropy regularization-based self-adaptive adjacent face image clustering method | |
| CN113065520B (en) | Multi-mode data-oriented remote sensing image classification method | |
| CN115100406B (en) | Weight information entropy fuzzy C-means clustering method based on superpixel processing | |
| CN111652836A (en) | Multi-scale target detection method based on clustering algorithm and neural network | |
| CN110991247B (en) | Electronic component identification method based on deep learning and NCA fusion | |
| CN115393631A (en) | Hyperspectral image classification method based on Bayesian layer graph convolution neural network | |
| CN116229061A (en) | Semantic segmentation method and system based on image generation | |
| CN113344069B (en) | Image classification method for unsupervised visual representation learning based on multi-dimensional relation alignment | |
| CN111652265A (en) | Robust semi-supervised sparse feature selection method based on self-adjusting graph | |
| CN117911771A (en) | Method for constructing training model for medical chest image disease classification based on Resnext integrated network | |
| CN117993282A (en) | Domain adaptability information bottleneck federal learning method for intelligent manufacturing fault diagnosis | |
| CN114898464B (en) | Lightweight accurate finger language intelligent algorithm identification method based on machine vision | |
| CN115131588A (en) | Image robust clustering method based on fuzzy clustering | |
| CN112257787B (en) | Image semi-supervised classification method based on generation type dual-condition confrontation network structure | |
| CN114299495A (en) | Small sample image classification method based on dimension self-adaption | |
| CN116229063B (en) | Semantic segmentation network model based on category colorization technology and training method thereof |
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 |