A high-dimensional indexing method for large-scale multimedia data based on locality-sensitive hashing

Abstract

The invention relates to a locality-sensitive-hashing-based high-dimensional indexing method for large-scale multimedia data. The method includes the following steps of extracting high-dimensional features of the multimedia data at the offline indexing stage; establishing an internal storage index, storing the multimedia high-dimensional features in a feature storage area, calculating the locality sensitive hashing vectors of the high-dimensional features, and storing feature numbers and the locality sensitive hashing vectors corresponding to the features in a hashing list storage area, wherein the internal storage index comprises the feature storage area and the hashing list storage area; establishing a first-stage disk index, wherein the first-stage disk index comprises a feature storage area, an index storage area and a plurality of hashing list storage areas; establishing a second-stage disk index, wherein the second-stage disk index comprises a hashing barrel storage area; repeatedly executing the steps mentioned above till all multimedia input is indexed. At the online query stage, features of the multimedia data used for queries are extracted, the queries are conducted on the basis of the established indexes, and similar query results are returned. By means of the method, the scheduling performance of internal storage and disks is improved, and the indexing speed and the retrieving speed of the multimedia data are increased.

Description

technical field [0001] The invention belongs to the technical field of multimedia indexing and retrieval, and in particular relates to a high-dimensional indexing method for large-scale multimedia data based on local sensitive hashing. Background technique [0002] In recent years, with the rapid development and popularization of Internet technology, especially the continuous promotion and application of social networking sites and image and video sharing sites, the number of images, audio and video on the Internet has shown a rapid growth trend. How to quickly and accurately retrieve the information users need from massive multimedia data has become an important problem to be solved urgently. Traditional text-based multimedia retrieval methods directly use the text information in web pages, which may not directly describe the multimedia content itself, so the accuracy is not high. Content-based image, audio and video retrieval can effectively overcome the above deficiencie...

AI Technical Summary

Problems solved by technology

However, one problem with multi-detection local sensitive hashing is that the algorithm can only store the index table in memory, and the amount of data it can support is small, so it cannot be widely used in current large-scale multimedia retrieval tasks.

In addition, because the IO performance of the disk is far worse than that of the memory, if the index is transferred from the memory to the disk, it will face the performance problem of the disk IO

Images