Image retrieval method based on content improved Average Hash

Abstract

The present invention discloses an image retrieval method based on content improved Average Hash. According to the method, the size of an image is reduced, grey-scale map processing is performed on the image, characteristics of a target image are obtained through repeated discrete cosine transform and Hash calculation processing; and matching operation is performed on the obtained characteristics and characteristics in an image characteristic library through similarity detection, and a retrieval result is obtained. By adoption of the method, a general image library can be effectively retrieved, and the detection effect is good; and certain deformed images can also be well tolerated.

Description

technical field

[0001] The invention belongs to the technical field of image retrieval, and in particular relates to an image retrieval method based on content-improved mean hash. Background technique

[0002] In recent years, with the rapid development of network and computer technology, society has entered the era of network data marked by big data. In recent years, many top international journals have successively published special issues to discuss the research on big data. Research on network data plays an important role in maintaining social stability, promoting social development, enhancing industry competitiveness, promoting emerging strategic industries, and scientific research methodology. The important part of network data—image, as multimedia information with rich information content, has become more and more mainstream of network data with the increasing popularity of the Internet and the continuous development of network technology. Coupled with the rapid deve...

Images