Image clustering method and system based on local chromatic features

Abstract

The invention discloses an image clustering method and system based on local chromatic features. A SURF-chromatic feature vector is extracted from each training image, K mean value clustering is carried out on the SURF-chromatic features of a whole training image set to obtain a feature vector dictionary; the SURF-chromatic feature vector is extracted from all images to be clustered, and a corresponding BOW feature vector is generated according to the feature vector dictionary; and DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering based on SNN (Shared Nearest Neighbor) similarity is carried out on the BOW feature vectors of all images to be clustered, and the images are subjected to corresponding category division according to the clustering. The method provided by the invention fully utilizes the local gray scale gradient and chromatic features of the image, has a better representational capability on the features of the image, and improves a clustering effect. In addition, when the images are clustered, the DBSCAN clustering method based on the SNN similarity can be used for processing clusters of different sizes, shapes and densities, and an image clustering effect can be improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image clustering method and system based on local chromaticity features of images. Background technique [0002] With the popularization of portable shooting devices such as digital cameras and smart phones, the number of digital images in people's daily life has exploded, and the demand for categorizing and managing these images is also increasing. Faced with a large amount of image data , manual sorting and classification is very time-consuming and laborious, and image clustering technology can alleviate this problem to a certain extent. Image clustering technology can divide a large number of messy images into multiple categories. Images belonging to the same category are similar to each other in a certain sense, while images belonging to different categories are very similar to each other, such as The images in one category are mostly football game images, while ...

AI Technical Summary

Problems solved by technology

At present, there are many feature extraction methods for clustering and cluster analysis, among which methods based on local features have been widely used, but many of these methods only consider the problem from the perspective of gray gradient features, while The role of chromaticity features is ignored, and there are no reports on clustering methods based on local chromaticity features of images

Images