Image retrieval method and image retrieval device

Abstract

The embodiment of the invention provides an image retrieval method and an image retrieval device. The method comprises the following steps: matching feature points of a queried image with visual words of a visual word list to obtain a first visual word collection; matching feature points of a candidate image with visual words of the visual word list to obtain a second visual word collection; determining a third visual word collection; aiming at the visual words in the third visual word collection, determining a feature point collection of the candidate image and a feature point collection of the queried image matched with the visual words in the third visual word collection; determining the space consistency similarities of the feature point collection of the candidate image and the feature point collection of the queried image; adding the space consistency similarities to obtain the space consistency similarities of the candidate image and the queried image; according to the space consistency similarities, determining the targeted retrieval image of the queried image. The image retrieval method and the image retrieval device, disclosed by the embodiment of the invention, can improve the accuracy of image retrieval.

Description

technical field [0001] Embodiments of the present invention relate to communication technologies, and in particular to an image retrieval method and device. Background technique [0002] With the development of Internet and multimedia technology, multimedia information, especially image information, is being generated and disseminated at an explosive speed. Image retrieval technology can enable users to quickly and accurately find and access the desired images in various image information, and has broad application prospects in the field of network multimedia. [0003] In the prior art, the commonly used image retrieval technology is mainly Content-Based Image Retrieval (CBIR for short), and the Bag Of visual Words (BOW for short) method has the best retrieval effect. One of the methods. The bag of visual words method refers to extracting the feature points of the query image under the premise of a given query image, matching these feature points with the visual word list,...

AI Technical Summary

Problems solved by technology

[0004] However, in the actual operation process, for the query image taken by the terminal or manually drawn, there may be unstable feature points due to human factors, which may lead to inaccurate images

Images