Multi-level mode sub block division-based image classification method

Abstract

The invention puts forward a multi-level mode sub block division-based image classification method. The method comprises the following steps: extracting a saliency area distribution diagram of an image under multiple scales and carrying out sampling of windows with different locations and sizes according to the saliency area distribution; implementing super-pixel segmentation on the image and determining target occurrence probability of each window by analyzing a position and distribution relation of each window and adjacent inner-outer super pixels so as to construct a multi-level mode sub block; carrying out multi-dictionary feature description on each sub block and carrying out organization to form tensor-mode image feature description; and carrying out a canonical correlation analysis on the tensor description of the image, extracting an image feature vector and carrying out classification by a classifier. On the basis of the multi-level mode sub block division, integrity and hierarchy of a target in a complex image are fully considered. On the one hand, centralized description of information in a same target mode is realized; and on the other hand, saliency description of information in different target modes can also be realized. The experiment result at a public testing image library confirms the effectiveness of the provided method.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to an image classification method based on multi-level pattern sub-block division. Background technique [0002] With the development of multimedia technology, multimedia data such as images and videos are increasing rapidly. How to quickly and effectively classify images is one of the current research hotspots in multimedia technology. As far as image classification is concerned, although different application backgrounds have different classification objectives and evaluation criteria, all image classification applications require image description first, and different image description methods are usually selected for different applications. Generally speaking, image description is to use a set of data to represent an image. This set of data can be in the form of vector or matrix. It is an abstract expression of image information and one of the important modules for im...

AI Technical Summary

Problems solved by technology

This image description method does not express the pattern information and target saliency information in the image, which leads to inaccurate image description

In addition, this method also has the problem that the same target in the image is separated, so that the appearance of the same target in different positions in the scene will form completely different feature descriptions. Therefore, the description of the overall information of the target in the image is lacking.

Images