Image retrieval method based on multiple intelligent algorithms and image fusion technology

Abstract

The invention discloses an image retrieval method based on multiple intelligent algorithms and an image fusion technology. According to the method, on the basis of a reinforced learning and genetic algorithm and a clustering algorithm, an intelligent learning framework for active learning is constructed; the image fusion technology and the genetic algorithm are used during relevant feedback, so that an inquiry vector and a similarity matching model are corrected; and the inquiry precision and the inquiry efficiency are improved. The image retrieval method has the advantages of higher inquiry precision and inquiry efficiency and relatively high robustness for translation, rotation and scale transformation; furthermore, after a certain number of inquiries and learning, intelligent retrieval can be realized; and the inquiry precision and the inquiry efficiency are further improved.

Description

technical field [0001] The invention relates to a content-based image retrieval method, in particular to an intelligent algorithm-based active learning image retrieval method. Background technique [0002] In the past ten years, with the rapid development and popularization of digital technology, multimedia data (images and videos, etc.) have become the most important data organization form besides text data. How to effectively organize and manage a large amount of multimedia data, and retrieve the information needed by users has become the most important research topic at present. Image data is the most basic and most commonly used form of multimedia. At the same time, the research on image retrieval is also the basis for the research on other multimedia forms. Therefore, the research on this aspect has become a hot spot in information retrieval. [0003] The traditional way of image retrieval is to manually label the image with text, and then use keyword-based retrieval t...

AI Technical Summary

Problems solved by technology

[0004] The initial retrieval results given by the content-based image retrieval system often cannot meet the information needs of users well, which is mainly due to the following points: First, due to the limitations of current image understanding Semantic mapping is still very difficult; secondly, due to the limitations of the user interface and unfamiliarity with the image library, it is difficult for users to give queries that can accurately reflect their information needs; in addition, due to the subjectivity of human visual perception, for the same image Different people or the same person may have different cognitions at different times, so off-line learning cannot adapt to these different requirements

Images