Multi-dimensional inverted index and quick retrieval algorithm for large-scale image visual features

Abstract

The invention discloses a multi-dimensional inverted index and quick retrieval algorithm for large-scale image visual features. The algorithm includes: training a multi-layer codebook required for enhanced residual quantification by visual features of images and building a multi-dimensional inverted index with the trained codebook; according to the trained codebook, quantifying and encoding the image visual features, and according to calculated codes, inserting the codes into corresponding inverted lists in the inverted index; querying the image visual features to query the built multi-dimensional inverted index so as to obtain a query candidate set; optimizing the query candidate set by adaptive hypersphere filtering, and ranking filtered query results so as to finish retrieval of the image visual features. The algorithm has the advantages that as the image features are quantified and encoded, efficiency of quantifying the image features is improved; the multi-dimensional inverted index is built with the generated image codes, the inverted index can be built just by training few codebooks, and speed of building the index structure is increased.

Description

technical field [0001] The invention belongs to the technical field of image retrieval, and more specifically relates to a multi-dimensional inverted index and fast retrieval algorithm for large-scale image visual features. Background technique [0002] At present, the development and popularization of the global network has reached an unprecedented scale, and the multimedia data represented by images from Weibo, mobile phones, social networking sites, news sites, and multimedia sharing sites is increasing at an alarming rate every day. Faced with a massive image library, only by effectively organizing the images for easy browsing, access and retrieval, can people quickly and accurately obtain the pictures they are interested in and love. Traditional text usually requires manual annotation of image content. However, as the size of the image database increases, manual annotation is time-consuming and laborious, and its limitations become more and more obvious. In addition, i...

AI Technical Summary

Problems solved by technology

[0005] Although a lot of research results have been achieved on the retrieval of image visual features, there is still room for further improvement in its retrieval performance.

Images