ERVQ image indexing and retrieval method in combination with semantic features

Abstract

The invention discloses ERVQ image indexing in combination with semantic features. The ERVQ image indexing method includes the following steps that an image set P1 for training indexing and an image set P2 to be indexed are prepared, low-level features of the P1, such as SIFT and SURF are extracted, training is conducted through a residual quantitative indexing (RVQ) training method, and an L-level RVQ code book1 is obtained, the Codebook 1 is adjusted through an ERVQ optimization method, a Codebook 2 is generated, multiple layers of center of mass of the Codebook 2 are combined one to one, and an indexing dictionary is built; each indexing entry of the indexing dictionary is divided into multiple posting list structures according to semantics, the low-level features and semantic features of the P2 are extracted, the indexing entries are found out according to the low-level features, and the indexing entries are inserted into the corresponding posting lists according to the semantic features, wherein the searching process includes the steps that the low-level features and the semantic features of the query image are extracted, the indexing entries are found out according to the low-level features, the posting lists on the indexing entries are found out according to the semantics, and finally, the multiple returned list images are sorted. By means of the indexing structure, the accuracy of the image query result based on the content can be improved, and the query time can be effectively shortened.

Description

technical field [0001] The invention belongs to the fields of computer vision and multimedia indexing, and more specifically relates to an ERVQ picture indexing and retrieval method combined with semantic features. Background technique [0002] Content-based image search is one of the hotspots of current research. Due to the huge number of images on the Internet, an efficient index structure must be built to achieve fast image retrieval. The first step in image indexing is to extract description features. The dimensionality of image description features is usually very high (for example, the scale-invariant feature transform (SIFT) feature has 128 dimensions), and it is very difficult to establish an efficient index on such a high dimension. big challenge. [0003] There are currently three main categories of image index structures: tree structure index, hash index, and visual word-based inverted index. When the vector dimension is too high, the tree structure index will f...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the defects of the prior art, the purpose of the present invention is to provide an ERVQ index structure and index retrieval algorithm combined with semantic features, aiming to solve the problem of inaccurate retrieval results existing in the existing methods

Images