Discrete supervision cross-modal hash retrieval method based on semantic preservation

Abstract

The invention discloses a discrete supervision cross-modal hash retrieval method based on semantic preservation, which realizes semantic-based image and text cross-modal retrieval, and comprises the following steps of: firstly, collecting an image and text sample pair from a network, and respectively extracting features of an image and a text sample; dividing the data set into a training set and atest set; learning a shared Hamming space for the image and text modalities by keeping semantic consistency of samples in the training set, and learning hash functions for the image and text modalities respectively; taking the training set and the test set as a target set and a query set respectively, and calculating Hamming distances between samples in the query set and heterogeneous samples inthe target set; and sorting from small to large according to the Hamming distance, and returning the sample sorted in the front as a retrieval result. According to the method, images and text samplescan be mapped to a shared Hamming space for efficient retrieval, the training speed is high, the accuracy is high, and the method has a good application prospect.

Description

technical field [0001] The invention relates to the fields of multimedia retrieval and pattern recognition, in particular to a discrete-supervised cross-modal hash retrieval method based on semantic preservation. Background technique [0002] With the rapid development of information technology and personal social networks, the data on the network not only increases rapidly, but also presents a variety of data representations, such as images, texts, voices, etc. This brings two challenges to multimedia retrieval: 1) how to achieve real-time retrieval in massive data; 2) retrieval across modalities. On the one hand, the amount of data on the network is very large, and the representation dimension of samples is also very high, even reaching tens of thousands of dimensions, so the traditional nearest neighbor retrieval method is difficult to apply on large-scale data sets. Hash method is one of the most effective methods to solve large-scale applications. Its idea is to map hi...

AI Technical Summary

Problems solved by technology

On the one hand, the similarity matrix between two samples is , in the era of big data The value of is very large, so this matrix usually leads to very high computational complexity and memory overhead, making it lose its scalability

On the other hand, using the Hamming distance between hash codes to approximate the similarity matrix between two samples is a decomposition problem of a symmetric matrix, which is difficult to solve

Images