CN112613583A - High-frequency information extraction clustering method for low-frequency noise face image - Google Patents
High-frequency information extraction clustering method for low-frequency noise face image Download PDFInfo
- Publication number
- CN112613583A CN112613583A CN202110009835.3A CN202110009835A CN112613583A CN 112613583 A CN112613583 A CN 112613583A CN 202110009835 A CN202110009835 A CN 202110009835A CN 112613583 A CN112613583 A CN 112613583A
- Authority
- CN
- China
- Prior art keywords
- sample
- matrix
- clustering
- frequency
- correlation coefficient
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Algebra (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computing Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a high-frequency information extraction clustering method for low-frequency noise face images, which comprises the following steps: s1: preprocessing the sample data set to obtain a plurality of sample matrixes; s2: extracting high-frequency information from the sample matrixes to correspondingly obtain a plurality of sample models with high-frequency characteristics reserved; s3: calculating a correlation coefficient matrix between the sample models; s4: constructing an initial Laplace matrix according to the correlation coefficient matrix; standardizing the initial Laplace matrix to obtain a standardized Laplace matrix L; s5: determining a dimension of a cluster as k1(ii) a Calculate the minimum front k of L1The characteristic vectors corresponding to the characteristic values are normalized according to lines to obtain n multiplied by k1A feature matrix of the dimension; s6: for n × k1Feature matrix of dimensionAnd clustering to obtain a clustering result. The invention provides a high-frequency information extraction clustering method for low-frequency noise face images, which solves the problem that the conventional clustering method cannot meet the clustering requirement of sparse data by using less computing resources.
Description
Technical Field
The invention relates to the technical field of image clustering, in particular to a high-frequency information extraction clustering method for low-frequency noise face images.
Background
Clustering analysis is an important research subject in the field of artificial intelligence, and clustering is a technology for searching internal structures among data, so that all data entities are combined into clusters. The cluster analysis has wide application in the fields of image recognition, commerce, biomedical science, insurance industry, electronic commerce and the like.
Traditional cluster analysis methods include partition-based, hierarchy-based, density-based, grid-based, model-based, and the like. The partition-based clustering method is a top-down method, a data set of a plurality of given data objects is divided into a plurality of partitions, each partition represents a cluster, and the K-Means algorithm is the most classical partition-based clustering method; the hierarchical clustering method is to carry out hierarchical decomposition on the specified data according to the requirements of certain conditions; the density-based method is to find high-density areas separated by low-density areas, namely starting from the density of a distribution area, and continuing clustering when the density of data objects exceeds a certain threshold, wherein the most representative method in the method is a DBSAN algorithm; the grid-based method is to put all the clusters on the grid for analysis, divide each attribute into adjacent intervals and create a set of cells; the model-based clustering method is to fit data with models, i.e. to fit data with models, and the assumed models are density functions of data objects in spatial distribution, etc. However, the conventional clustering method needs more computing resources when clustering, and cannot meet the clustering requirement of sparse data with less computing resources.
In the prior art, as disclosed in the chinese patent 2019-03-08, an image clustering method based on a depth matrix decomposition with dual-map sparsity, which is disclosed as CN109447147A, is used to solve the technical problems of low image clustering accuracy and slow operation speed in a clustering process in the prior art, but cannot meet the clustering requirement of sparse data with less computing resources.
Disclosure of Invention
The invention provides a high-frequency information extraction clustering method for low-frequency noise face images, aiming at overcoming the technical defect that the conventional clustering method cannot meet the clustering requirement of sparse data by using less computing resources.
In order to solve the technical problems, the technical scheme of the invention is as follows:
a high-frequency information extraction clustering method for low-frequency noise face images comprises the following steps:
s1: preprocessing the sample data set to obtain a plurality of sample matrixes;
s2: extracting high-frequency information from the sample matrixes to correspondingly obtain a plurality of sample models with high-frequency characteristics reserved;
s3: calculating a correlation coefficient matrix between the sample models;
s4: constructing an initial Laplace matrix according to the correlation coefficient matrix;
standardizing the initial Laplace matrix to obtain a standardized Laplace matrix L;
s5: determining a dimension of a cluster as k1；
Calculate the minimum front k of L1The characteristic vectors corresponding to the characteristic values are normalized according to lines to obtain n multiplied by k1A feature matrix of the dimension; wherein n is the number of image samples in the sample data set;
s6: for n × k1And clustering the dimensional characteristic matrix to obtain a clustering result.
Preferably, the sample data set is a mat file generated by compressing pixel points of n image samples.
Preferably, in step S1, the preprocessing the sample data set specifically includes: filling and restoring each vector in the sample data set into a corresponding sample matrix according to the length and the width of the image sample;
wherein the value of each pixel in the sample matrix is between 0 and 255.
Preferably, in step S2, the extracting the high frequency information from the sample matrix includes the following steps:
s2.1: performing two-dimensional Fourier transform on the sample matrix to obtain an original frequency spectrum;
s2.2: symmetrically transforming the original frequency spectrum to obtain a ffftshift image;
s2.3: designing a Butterworth filter, and enabling the ffftshift image to pass through the Butterworth filter;
s2.4: and performing Fourier inverse transformation on the ffftshift image passing through the Butterworth filter to obtain a sample model with high-frequency characteristics.
Preferably, before performing two-dimensional fourier transform on the sample matrix, the method further includes performing value transform on the sample matrix.
Preferably, the order of the butterworth filter is 2 orders and the cut-off frequency is 5% of the image sample width.
Preferably, in step S3, the correlation coefficient matrix between the sample models is determined by:
regarding the sample models as energy signal sequences, calculating the correlation between the two sample models, namely comparing the similarity between the two energy signals, wherein the comparison result value is the cross-correlation coefficient of the two energy signal sequences, the value is from 0 to 1, and the higher the value is, the more similar the sample results are; and (3) circularly calculating the cross correlation coefficient between every two to obtain a correlation coefficient matrix.
Preferably, obtaining the correlation coefficient matrix further includes: and intercepting the first K maximum values in the correlation coefficient matrix as a simplified correlation coefficient matrix W.
Preferably, in step S4, the method specifically includes the following steps:
s4.1: obtaining a degree matrix D according to the simplified correlation coefficient matrix W;
s4.2: construction of an initial Laplace matrix L1＝D-W；
S4.3: construction of standardized PullThe placian matrix L ═ D-1/2L1D-1/2。
Preferably, in step S6, the K-Means algorithm is applied to n × K1Clustering the feature matrix of the dimension to obtain a clustering result; the clustering result is that the clusters are divided into C ═ C1，C2，...，Ck2(ii) a Where k2 is the number of clusters.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that:
the invention provides a high-frequency information extraction clustering method for low-frequency noise face images, which only retains the most important characteristics by extracting high-frequency information of a sample matrix, reduces the computing resources required by clustering and realizes that the clustering requirement of sparse data is met by using less computing resources.
Drawings
FIG. 1 is a flow chart of the steps for implementing the technical solution of the present invention;
FIG. 2 is a sample of a portion of an image obtained by padding reduction according to the present invention;
FIG. 3 is a ffftshift image obtained by symmetric transformation in the present invention;
FIG. 4 is a sample image before high frequency information extraction according to the present invention;
fig. 5 is an image sample after high frequency information extraction in the present invention.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent;
for the purpose of better illustrating the embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product;
it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
Example 1
As shown in fig. 1, a method for extracting and clustering high-frequency information of low-frequency noise face images includes the following steps:
s1: preprocessing the sample data set to obtain a plurality of sample matrixes;
s2: extracting high-frequency information from the sample matrixes to correspondingly obtain a plurality of sample models with high-frequency characteristics reserved;
s3: calculating a correlation coefficient matrix between the sample models;
s4: constructing an initial Laplace matrix according to the correlation coefficient matrix;
standardizing the initial Laplace matrix to obtain a standardized Laplace matrix L;
s5: determining a dimension of a cluster as k1；
Calculate the minimum front k of L1The characteristic vectors corresponding to the characteristic values are normalized according to lines to obtain n multiplied by k1A feature matrix of the dimension; wherein n is the number of image samples in the sample data set;
s6: for n × k1And clustering the dimensional characteristic matrix to obtain a clustering result.
Example 2
More specifically, the sample data set is a mat file generated by compressing pixel points of n image samples.
In this embodiment, a mat file with a sample data set of 2200 × 260 is set, where 260 is the number of image samples, and 2200 is a vector formed by stretching sample data in the sample data set.
More specifically, in step S1, the preprocessing of the sample data set specifically includes: filling and restoring each vector in the sample data set into a corresponding sample matrix according to the length and the width of the image sample;
wherein the value of each pixel in the sample matrix is between 0 and 255.
In the implementation, the image is a standard rectangle, and the length and width of the image are expressed by the rows and columns of the matrix. The sample data set is a matrix formed by stretching a standard matrix corresponding to each image sample into a column. In this embodiment, the length and width of the image are set to be 55 × 40, fig. 2 shows the restored partial image samples, and 10 samples in each row are the same cluster.
More specifically, in step S2, the extracting of the high frequency information from the sample matrix includes the following steps:
s2.1: performing two-dimensional Fourier transform on the sample matrix to obtain an original frequency spectrum, wherein the high frequency is in the middle, and the low frequency is around;
s2.2: carrying out symmetric transformation on an original frequency spectrum, and obtaining a ffftshift (moving a zero frequency point to the middle of the frequency spectrum) image with a low frequency in the middle and a high frequency around as shown in fig. 3;
s2.3: designing a Butterworth filter, and enabling the ffftshift image to pass through the Butterworth filter;
s2.4: the ffftshift image passing through the Butterworth filter is subjected to Fourier inversion to obtain a sample model with high-frequency characteristics, the high-frequency characteristics, namely the outline shape of the image, are reserved, the low-frequency characteristics are filtered, and the interference of a low-frequency section on subsequent clustering analysis is reduced, as shown in FIGS. 4-5.
In the specific implementation process, the sample matrix has higher dimensionality, simultaneously represents that data is sparse, and is greatly influenced by noise when clustering analysis is carried out. The image sample comprises a low-frequency part and a high-frequency part, wherein the low-frequency part is gradually changed in color, namely, the gray level is slowly changed and represents a continuously gradually changed area in the image, the high-frequency part is quickly changed in frequency and obviously and violently changed in gray level, the gray level of the edge of one image and the background part is quickly changed, and the image contour of the sample is highlighted, namely, the high-frequency part of the image represents the rough information of the image contour.
More specifically, before performing two-dimensional fourier transform on the sample matrix, the method further comprises performing value transform on the sample matrix.
In the implementation process, the accuracy can be ensured by transforming the values, and the loss of the values during the two-dimensional Fourier transform (FFT2) transformation can be avoided.
More specifically, the order of the butterworth filter is 2 orders, and the cut-off frequency is 5% of the image sample width.
In the implementation, the ffftshift image is passed through a butterworth filter, so that the frequency response curve in the pass band is flat to the maximum extent, and gradually drops to zero in the stop band. The low frequency band in the image sample is filtered, most high frequency bands are reserved, the possibility of reducing the dimension for clustering analysis is realized, the interference of low frequency characteristics is reduced, and the clustering accuracy is improved.
More specifically, in step S3, a correlation coefficient matrix between the sample models is determined by:
regarding the sample model as an energy signal sequence, calculating the correlation between the two sample models, namely comparing the similarity between the two energy signals, wherein the comparison result is the cross-correlation coefficient of the two energy signal sequences
Wherein gamma isxyIs the inner product of sequence X and sequence Y, gammaxxAnd gammayyRespectively the inner products of the sequence X and the sequence Y to obtain the cross correlation coefficient rhoxyIn order to obtain the correlation between the two corresponding sample models, the value is from 0 to 1, and the higher the value is, the more similar the sample results are; and (3) circularly calculating the cross correlation coefficient between every two to obtain a correlation coefficient matrix.
In the specific implementation process, the method for obtaining the correlation coefficient matrix by using Gaussian kernel function calculation is avoided, and the efficiency and the accuracy of operation are improved.
More specifically, obtaining the correlation coefficient matrix further includes: and intercepting the first K maximum values in the correlation coefficient matrix as a simplified correlation coefficient matrix W.
In a specific implementation process, the sample data set of this embodiment includes 260 images, and the number of clusters is only 10, which means that the number of each image sample and its class is about several tens, so that the correlation coefficient matrix can be simplified, only the top K item with the largest similarity is taken, the value after the top K item with the highest correlation is set to 0 in the correlation coefficient matrix, and setting a proper K value can improve the calculation efficiency in the clustering process, and the clustering accuracy is also sufficiently guaranteed. To obtain the best clustering effect, the present embodiment sets the K value to 260 as fully connected.
More specifically, step S4 specifically includes the following steps:
s4.1: obtaining a degree matrix D according to the simplified correlation coefficient matrix W;
s4.2: construction of an initial Laplace matrix L1＝D-W；
S4.3: constructing a normalized Laplace matrix L ═ D-1/2L1D-1/2。
In the implementation process, a degree matrix D is obtained by adding values of each row of the relational number matrix W on a diagonal line, and assigning other values to 0.
More specifically, in step S6, the K-Means algorithm is applied to n × K1Clustering the feature matrix of the dimension to obtain a clustering result; the clustering result is that the clusters are divided into C ═ C1，C2，...，Ck2(ii) a Where k2 is the number of clusters.
In the implementation process, the dimension k of the cluster is reduced1The efficiency of the operation can be improved. In this embodiment, k is set1Therefore, the eigenvectors corresponding to the minimum first 14 eigenvalues of L are calculated, the eigenvectors corresponding to the eigenvectors are normalized by rows to obtain a 260 × 14 eigenvector matrix, each row of the eigenvector matrix is used as a 14-dimensional sample, and the dimension reduction operation of the samples from 2200 to 14 is realized, so that 260 samples are counted in total; the clustering number k2 is set to 10, resulting in a cluster division C ═ C1，C2，...，C10。
Example 3
Table 1 compares the effects of the three clustering methods.
TABLE 1
The sample data set used is 10 persons × 26 faces, no labels, i.e. 260 image samples in total, the number of categories is set to 10, and the height and width of the image are set to 55 and 40, respectively. As can be seen from Table 1, the indexes of the high-frequency information extraction clustering method for the low-frequency noise face image, such as accuracy, are greatly improved compared with the traditional K-means algorithm.
It should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. A high-frequency information extraction clustering method for low-frequency noise face images is characterized by comprising the following steps:
s1: preprocessing the sample data set to obtain a plurality of sample matrixes;
s2: extracting high-frequency information from the sample matrixes to correspondingly obtain a plurality of sample models with high-frequency characteristics reserved;
s3: calculating a correlation coefficient matrix between the sample models;
s4: constructing an initial Laplace matrix according to the correlation coefficient matrix;
standardizing the initial Laplace matrix to obtain a standardized Laplace matrix L;
s5: determining a dimension of a cluster as k1；
Calculate the minimum front k of L1The characteristic vectors corresponding to the characteristic values are normalized according to lines to obtain n multiplied by k1A feature matrix of the dimension; wherein n is the number of image samples in the sample data set;
s6: for n × k1And clustering the dimensional characteristic matrix to obtain a clustering result.
2. The method according to claim 1, wherein the sample data set is a mat file generated by compressing pixel points of n image samples.
3. The method for extracting and clustering high-frequency information of low-frequency noise face images according to claim 2, wherein in step S1, the preprocessing of the sample data set specifically comprises: filling and restoring each vector in the sample data set into a corresponding sample matrix according to the length and the width of the image sample;
wherein the value of each pixel in the sample matrix is between 0 and 255.
4. The method for extracting and clustering high-frequency information of low-frequency noise face images according to claim 1, wherein in step S2, the extracting high-frequency information of the sample matrix comprises the following steps:
s2.1: performing two-dimensional Fourier transform on the sample matrix to obtain an original frequency spectrum;
s2.2: symmetrically transforming the original frequency spectrum to obtain a ffftshift image;
s2.3: designing a Butterworth filter, and enabling the ffftshift image to pass through the Butterworth filter;
s2.4: and performing Fourier inverse transformation on the ffftshift image passing through the Butterworth filter to obtain a sample model with high-frequency characteristics.
5. The method for extracting and clustering high-frequency information of low-frequency noise face images according to claim 4, wherein before performing two-dimensional Fourier transform on the sample matrix, the method further comprises performing value transform on the sample matrix.
6. The method as claimed in claim 4, wherein the order of the Butterworth filter is 2, and the cut-off frequency is 5% of the width of the image sample.
7. The method for extracting and clustering high-frequency information of low-frequency noise face images according to claim 1, wherein in step S3, a correlation coefficient matrix between each sample model is determined by the following steps:
regarding the sample models as energy signal sequences, calculating the correlation between the two sample models, namely comparing the similarity between the two energy signals, wherein the comparison result value is the cross-correlation coefficient of the two energy signal sequences, the value is from 0 to 1, and the higher the value is, the more similar the sample results are; and (3) circularly calculating the cross correlation coefficient between every two to obtain a correlation coefficient matrix.
8. The method for extracting and clustering high-frequency information of low-frequency noise facial images according to claim 1, wherein obtaining the correlation coefficient matrix further comprises: and intercepting the first K maximum values in the correlation coefficient matrix as a simplified correlation coefficient matrix W.
9. The method for extracting and clustering high-frequency information of low-frequency noise face images according to claim 8, wherein in step S4, the method specifically comprises the following steps:
s4.1: obtaining a degree matrix D according to the simplified correlation coefficient matrix W;
s4.2: construction of an initial Laplace matrix L1＝D-W；
S4.3: constructing a normalized Laplace matrix L ═ D-1/2L1D-1/2。
10. The method for extracting and clustering high-frequency information of low-frequency noise face images as claimed in claim 1, wherein in step S6, n x K is determined by using K-Means algorithm1Clustering the feature matrix of the dimension to obtain a clustering result; the above-mentionedThe clustering result is that the clusters are divided into C ═ C1，C2，...，Ck2(ii) a Where k2 is the number of clusters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110009835.3A CN112613583B (en) | 2021-01-05 | 2021-01-05 | High-frequency information extraction clustering method for low-frequency noise face image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110009835.3A CN112613583B (en) | 2021-01-05 | 2021-01-05 | High-frequency information extraction clustering method for low-frequency noise face image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112613583A true CN112613583A (en) | 2021-04-06 |
| CN112613583B CN112613583B (en) | 2023-07-21 |
Family
ID=75253318
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110009835.3A Active CN112613583B (en) | 2021-01-05 | 2021-01-05 | High-frequency information extraction clustering method for low-frequency noise face image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112613583B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113313394A (en) * | 2021-06-02 | 2021-08-27 | 马鞍山钢铁股份有限公司 | Coke quality evaluation method |
| CN117576493A (en) * | 2024-01-16 | 2024-02-20 | 武汉明炀大数据科技有限公司 | Cloud storage compression method and system for large sample data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563287A (en) * | 2017-06-16 | 2018-01-09 | 江汉大学 | Face identification method and device |
| CN108647726A (en) * | 2018-05-11 | 2018-10-12 | 南京理工大学 | A kind of image clustering method |
| CN109190661A (en) * | 2018-07-26 | 2019-01-11 | 安徽师范大学 | A kind of Spectral Clustering based on difference secret protection |
| CN110349101A (en) * | 2019-06-26 | 2019-10-18 | 上海集成电路研发中心有限公司 | A kind of multiple dimensioned united Wavelet image denoising method |
-
2021
- 2021-01-05 CN CN202110009835.3A patent/CN112613583B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563287A (en) * | 2017-06-16 | 2018-01-09 | 江汉大学 | Face identification method and device |
| CN108647726A (en) * | 2018-05-11 | 2018-10-12 | 南京理工大学 | A kind of image clustering method |
| CN109190661A (en) * | 2018-07-26 | 2019-01-11 | 安徽师范大学 | A kind of Spectral Clustering based on difference secret protection |
| CN110349101A (en) * | 2019-06-26 | 2019-10-18 | 上海集成电路研发中心有限公司 | A kind of multiple dimensioned united Wavelet image denoising method |
Non-Patent Citations (1)
| Title |
|---|
| 夏平;任强;吴涛;雷帮军;: "融合多尺度统计信息模糊C均值聚类与Markov随机场的小波域声纳图像分割", 兵工学报, no. 05, pages 111 - 119 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113313394A (en) * | 2021-06-02 | 2021-08-27 | 马鞍山钢铁股份有限公司 | Coke quality evaluation method |
| CN117576493A (en) * | 2024-01-16 | 2024-02-20 | 武汉明炀大数据科技有限公司 | Cloud storage compression method and system for large sample data |
| CN117576493B (en) * | 2024-01-16 | 2024-04-02 | 武汉明炀大数据科技有限公司 | Cloud storage compression method and system for large sample data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112613583B (en) | 2023-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110348399B (en) | Hyperspectral intelligent classification method based on prototype learning mechanism and multidimensional residual error network | |
| Jalba et al. | Morphological hat-transform scale spaces and their use in pattern classification | |
| CN104268593A (en) | Multiple-sparse-representation face recognition method for solving small sample size problem | |
| CN104299003A (en) | Gait recognition method based on similar rule Gaussian kernel function classifier | |
| CN109766934B (en) | Image target identification method based on depth Gabor network | |
| CN112613583A (en) | High-frequency information extraction clustering method for low-frequency noise face image | |
| Lakshmi et al. | A rough set based subspace clustering technique for high dimensional data | |
| CN106803105B (en) | Image classification method based on sparse representation dictionary learning | |
| Liu et al. | Improving image retrieval by integrating shape and texture features | |
| CN110991554A (en) | Improved PCA (principal component analysis) -based deep network image classification method | |
| CN108985346B (en) | Existing exploration image retrieval method fusing low-level image features and CNN features | |
| CN110674848A (en) | High-dimensional data joint clustering method combining sparse representation and bipartite graph segmentation | |
| CN111553417B (en) | Image data dimension reduction method and system based on discriminant regularization local preserving projection | |
| Ayyavoo et al. | Face recognition using enhanced energy of discrete wavelet transform | |
| CN112541874A (en) | Unsupervised denoising feature learning method based on self-encoder | |
| CN108052867A (en) | A kind of single sample face recognition method based on bag of words | |
| CN112001231A (en) | Three-dimensional face recognition method, system and medium for weighted multi-task sparse representation | |
| CN112818779B (en) | Human behavior recognition method based on feature optimization and multiple feature fusion | |
| Thamizharasi | Performance analysis of face recognition by combining multiscale techniques and homomorphic filter using fuzzy K nearest neighbour classifier | |
| da Silva et al. | Satellite image segmentation using wavelet transforms based on color and texture features | |
| Melinda et al. | Implementation of segmentation scheme based on wavelet transform in multi-spectral fluctuation patterns | |
| Chitaliya et al. | Comparative analysis using fast discrete Curvelet transform via wrapping and discrete Contourlet transform for feature extraction and recognition | |
| CN109978066B (en) | Rapid spectral clustering method based on multi-scale data structure | |
| Azam et al. | Bounded Laplace mixture model with applications to image clustering and content based image retrieval | |
| Verma et al. | Multi-resolution Local extrema patterns using discrete wavelet transform |
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 |