Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A robust image clustering method

An image clustering and robust technology, applied in the field of pattern recognition, can solve problems such as clustering center offset

Active Publication Date: 2019-03-29
NANJING UNIV OF SCI & TECH
View PDF7 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to propose a robust image clustering method, which solves the problem of cluster center offset caused by outliers in traditional clustering problems

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A robust image clustering method
  • A robust image clustering method
  • A robust image clustering method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] Such as figure 1 As shown, a robust image clustering method uses the similarity information of the original image to construct a Laplacian matrix, and extracts its eigenvalues ​​and eigenvectors. On the premise of keeping the original image’s neighborhood structure information unchanged, the extracted feature vector contains the clustering information, and the Welsch function is used to limit the influence of the outliers on the clustering center, and the original image data is obtained. A new representation of discriminative power. Finally, k-means clustering is used to obtain the new representation to effectively and accurately cluster the image. The specific steps are as follows:

[0040] Step 1. Perform normalization processing and feature extraction on the original image data. For n original image data x 1 ,x 2 ,...,x n The pixel values ​​are normalized so that each pixel value is between 0 and 1. Extract features from the processed image, such as Histogram of ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a robust image clustering method. Firstly, the original image data is normalized and the features are extracted. The K-nearest neighbor graph G is constructed for the processedimage data, and the Laplace matrix L is calculated according to the adjacency matrix W and the corresponding degree matrix D of the K-nearest neighbor graph G; The Laplace matrix L is decomposed intoeigenvalues, and the obtained eigenvectors are sorted from small to large according to the corresponding eigenvalues, and p eigenvectors are sequentially selected to form a candidate eigenvector matrix U, and p is the number of clusters; Then, the objective function is constructed according to the Laplace matrix and the candidate eigenvector set, and the objective function is solved to obtain thediscriminant representation Y* of the original image data. Finally, the distinguishing representation Y* is given by k-mean value clustering, the final clustering results are obtained. The invention can cluster not only the simple image data set, but also the complex image data with divorced points.

Description

technical field [0001] The invention belongs to the field of pattern recognition, in particular to a robust image clustering method. Background technique [0002] In the field of pattern recognition, cluster analysis of images is a very basic type of research content. Its goal is to classify similar images into one category according to the characteristics of the image, so that the original image data can be divided into different categories. In the real world, it is difficult to obtain a large amount of annotated image data because it is expensive to annotate a large amount of image data. In this case, by clustering and analyzing the image data, the image features and the distribution of the image data can be preliminarily obtained, which can provide convenience for subsequent processing. Therefore, cluster analysis of image data is an indispensable work. [0003] Frey et al. proposed the AP (Affinity Propagation) algorithm, whose idea is to use all data points as candid...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/62
CPCG06F18/23213
Inventor 柯京辰宫辰
Owner NANJING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com