Hash image retrieval method and device based on generalized average pooling strategy

Abstract

The invention relates to a Hash image retrieval method and device based on a generalized average pooling strategy. The method comprises the following steps: establishing a feature index of an image feature library; performing feature extraction on the to-be-retrieved image by using a pre-trained feature extraction network to obtain a feature vector of the to-be-retrieved image; mapping the feature vector of the to-be-retrieved image by using a locality sensitive Hash algorithm, and mapping the feature vector into a Hash bucket; according to the feature index, searching to obtain an image feature vector corresponding to the hash bucket; and calculating the similarity between the to-be-retrieved image feature vector and the image feature vector corresponding to the hash bucket, sorting according to the distance from small to large, outputting the first k retrieval results, k being a positive integer, and completing the image retrieval. According to the retrieval method, the process of retrieving the similar images in the image library can be accelerated, and rapid matching of the to-be-retrieved images in the image library is realized.

Description

technical field [0001] The invention belongs to the technical field of digital image processing, and in particular relates to a hash image retrieval method and device based on a generalized average pooling strategy. Background technique [0002] Image retrieval technology aims at the image content that users are interested in, and presents related images to users in a manner of increasing similarity from high to low according to a specific similarity measurement standard. The core problem is how to condense the information of the image, obtain the feature descriptor of the image, and fully express the content information of the image. In recent years, with the rapid development of Internet technology, a large amount of information overload, how to conveniently, quickly and accurately query and retrieve image data in the huge image database is still an unsolved problem. [0003] The problem of large-scale image retrieval has problems such as high dimensionality, large amount...

AI Technical Summary

Problems solved by technology

The traditional pooling strategy treats the extracted local feature maps equally, which does not conform to the nonlinear characteristics of the human visual system, and the existing retrieval methods will have problems such as lack of effective feature information of the image and slow retrieval speed under large-scale data.

Images