Web Image Retrieval Method Based on Semantic Propagation and Hybrid Multi-Instance Learning

Abstract

The invention belongs to the technical field of image processing, and specifically provides a Web image retrieval method based on semantic propagation and hybrid multi-instance learning, which combines the visual features of the image with text information to perform Web image retrieval, and first expresses the image as a BoW model, Then the images are clustered according to the visual similarity and text similarity, and the semantic features of the image are propagated to the visual feature vector of the image through the common visual vocabulary in the text class; in the relevant feedback stage, a hybrid multi-instance Learning algorithm to solve the small sample problem in the actual retrieval process. Compared with the traditional CBIR framework, this retrieval method uses the text information of Internet images in a cross-modal manner to propagate the semantic features of the image to the visual features, and introduces semi-supervised learning in the relevant feedback based on multi-instance learning to deal with the small sample problem. It can effectively reduce the semantic gap and improve the performance of Web image retrieval.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a Web image retrieval method based on semantic propagation and mixed multi-instance learning. Background technique [0002] In the network environment, images are generally embedded in Web pages and published with rich text information, such as tags, file names, URL information, and image context. For Web image retrieval, TBIR (Text-based Image Retrieval) based on text information and CBlR (Content-based Image Retrieval) based on image visual features have their own advantages and disadvantages. To a certain extent, TBIR avoids the problem of identifying complex visual elements, makes full use of web page context and hypertext structure information, and conforms to people's familiar retrieval habits, and is simple to implement. However, because it is still limited to the scope of text retrieval, it uses controlled vocabulary To describe the image, it is pron...

AI Technical Summary

Problems solved by technology

However, this method will generate a very large and complex relationship network in the process of relationship propagation, and the calculation is complex; moreover, the propagation process will generate a large number of auxiliary visual vocabulary, thereby reducing the accuracy of image retrieval

Images