Interactive image retrieval method

Abstract

An indexing-method of interactive image includes selecting out interest region by user, carrying out automatic analysis on selected interest region to pick up Its feature and applying scan mode to carry out index.

Description

technical field [0001] The invention proposes an interactive image retrieval method, which solves the problem that it is difficult to extract the image region that accurately expresses the user's retrieval intention due to the lack of high-level semantic knowledge through the user's selection of the region of interest. With the help of the user's simple operation, accurate query information is obtained, and the retrieval efficiency of the retrieval system is effectively improved. Background technique [0002] With the rapid development of multimedia technology, the capacity of digital images is increasing at an alarming rate. How to quickly and accurately find the image you need from a large amount of image data is not only the most urgent need of users, but also the main task of image retrieval. Compared with traditional keyword and text-based image retrieval methods, content-based image retrieval (CBIR) [1，2] It uses the color, texture, shape and other features of the im...

AI Technical Summary

Problems solved by technology

For content-based image retrieval systems, it is generally not possible to use text and keywords to query, because the richness and complexity of image content and the differences in people's understanding of the same image make it difficult to accurately describe the content of an image in words

Images