Depth feature-based image retrieval method and apparatus

Abstract

The invention provides a depth feature-based image retrieval method and apparatus. The method comprises the steps of obtaining an image sample set; cutting each image in the image sample set into a plurality of image blocks with independent semanteme; extracting corresponding image features from the image blocks, and performing clustering operation on the extracted image features to determine visual words corresponding to the image features; constructing eigenvectors corresponding to the images in the image sample set according to the determined visual words, and forming an image index library through the eigenvectors; obtaining a to-be-retrieved target image, and extracting a target eigenvector corresponding to the target image; and matching the target eigenvector with the eigenvectors in the image index library, and feeding back a retrieval result of the target image according to a matching result. According to the depth feature-based image retrieval method and apparatus provided by the invention, the image retrieval precision can be improved.

Description

technical field [0001] The invention relates to the technical field of image retrieval, in particular to an image retrieval method and device based on depth features. Background technique [0002] With the rapid development of information technology, the growth rate of image data on the Internet is astonishing. It has become an urgent need for users to find a desired image quickly and accurately. Content-based image retrieval (Content-based Image Retrieval, CBIR) is to use machine learning and image processing technology to solve the problems in image retrieval. Although the content-based image retrieval technology has been studied for many years, due to the existence of "semantic gap", the current content-based image retrieval system is still difficult to meet people's daily retrieval needs. A high-precision content-based image retrieval system mainly depends on two key technologies: first, how to represent images as an effective retrieval feature to achieve high-precisio...

AI Technical Summary

Problems solved by technology

But in general, whether it is an image retrieval system based on global features or local features, it does not deviate from the mode of using artificially designed image feature description, which limits the expressive ability of features, thus restricting the accuracy of the image retrieval system.

Images