Image retrieval method and device

Abstract

The invention discloses an image retrieval method and an image retrieval device and relates to the field of image search. The method comprises the steps of extracting global characteristics of a picture and then carrying out dimension reduction; quantifying the characteristics into binary bit strings; and retrieving similar pictures from a database according to a distance of the binary bit strings. According to the image retrieval method and the image retrieval device, the description for the picture is accurate by use of the global characteristics, the data size of picture characteristics can be decreased through dimension reduction for the global characteristics, meanwhile as a dimension reduction model can allow the distance of the global characteristics, subjected to dimension reduction, of a picture to be decreased and the distance of the global characteristics subjected to dimension reduction of dissimilar pictures increases, the descriptive power is improved after the global characteristics of the picture are subjected to dimension reduction; furthermore, the picture characteristics are quantified into the the binary bit strings, the data complexity can be reduced, the data storage volume is decreased, the matching complexity during retrieval is reduced, the retrieval efficiency is improved, and the image retrieval processing power is enhanced to hundreds of millions of magnitude orders.

Description

technical field [0001] The invention relates to the field of image search, in particular to an image search method and device. Background technique [0002] With the development of Internet technology, users' demand for data retrieval is getting higher and higher. Users are not only satisfied with the retrieval results obtained by text and voice input, but also hope to obtain satisfactory matching results by inputting images. For example, users conduct online The shopper may not know the brand, model, etc. of the product they want to buy, and cannot accurately describe its characteristics, but the user has a picture taken, and the user hopes to input the picture to retrieve the product he wants to buy. [0003] At present, the more commonly used image retrieval technology is the product quantization algorithm. This algorithm is more complicated to describe the image features and takes up a lot of memory. In the face of massive data in the Internet, it cannot support the calc...

AI Technical Summary

Problems solved by technology

[0002] With the development of Internet technology, users' demand for data retrieval is getting higher and higher. Users are not only satisfied with the retrieval results obtained by text and voice input, but also hope to obtain satisfactory matching results by inputting images. For example, users conduct online Shopping may not know the brand, model, etc. of the product you want to buy, and you cannot accurately describe its characteristics, but the user has a picture taken, and the user hopes to enter the picture to retrieve the product you want to buy

[0003] At present, the more commonly used image retrieval technology is the product quantization algorithm. This algorithm is more complicated to describe the image features and takes up a lot of memory. In the face of massive data in the Internet, it cannot support the calculation and matching process of a large number of images. It can support tens of millions of image processing, which cannot meet the needs of users

Images