An Image Retrieval Method Based on Multi-Index Disk Hash Structure

Abstract

The invention relates to an image retrieval method for a multi-index disk Hash structure. The method comprises the following steps that in an offline index stage, high-dimensional features are extracted from media data; a Hash mapping method is adopted for mapping the high-dimensional features into Hash codes; the Hash codes are averagely partitioned into code substrings; the code substrings are inserted into corresponding B+ tree index structures based on a disk respectively; the steps are repeated m times, and the multi-index disk Hash structure is formed. In an on-line inquiry stage, the inquired media data is subjected to feature extraction, Hash coding and code partitioning, then the code substrings are obtained, r neighbor results of the codes in disk indexes are searched and combined till a k neighbor result is found, and the steps return. The advantages of the multi-index Hash method and the advantages of a B+ tree storage structure are combined, the retrieval accuracy and retrieval speed of the index structure are improved, and meanwhile the supported data volume is increased.

Description

technical field [0001] The invention relates to the technical field of image indexing and retrieval, in particular to an image retrieval method with a multi-index disk hash structure. Background technique [0002] In recent years, with the advancement of the "Internet +" policy, my country's Internet technology, digital media technology, and network transmission technology have flourished. The popularity of terminal devices such as smartphones and tablets, as well as the continuous development of social applications and e-commerce applications, have led to a rapid increase in image data. In order to make better use of these image data, fast and accurate large-scale image data retrieval has become an important problem to be solved urgently. Traditional text-based image retrieval relies on highly subjective text information such as image names or annotations, and often fails to achieve the desired retrieval effect. Content-based image retrieval uses image features such as co...

AI Technical Summary

Problems solved by technology

Since the IO efficiency of the disk is lower than that of the memory, how to design a reasonable index structure to optimize the IO strategy of the disk while maintaining the retrieval performance of the multi-index hash structure has become a key issue to solve the efficient retrieval of hash coding

Images