Unsupervised hash image retrieval system and method based on convolution neural network

Abstract

The present invention proposes an unsupervised hash image retrieval system and method based on the convolution neural network. The system and method based on the data enhancement technology, proposes an efficient unsupervised hash model used for the field of fast image retrieval by using the existing hash algorithm structure. Through the data enhancement method, a triad training sample is constructed for the unlabeled data; and the triad loss function, the minimum quantization error loss function and the maximum entropy loss function drive the network to make full use of the information of each picture, so that a series of parameters with more expressive ability is learned to improve the accuracy of fast picture retrieval. The method provided by the present invention is a hash fast image retrieval method capable of using the unlabeled data learning network, the data enhancement is used to construct the triad training sample with more powerful expression ability to train the network, and the accuracy of fast picture retrieval is significantly improved.

Description

Technical field [0001] The present invention relates to the fields of computer vision and image processing, and in particular to an unsupervised hash fast image retrieval system and method based on convolutional neural network. Background technique [0002] With the explosive growth of existing multimedia content, how to speed up image retrieval has attracted widespread attention. Hash, as an algorithm that can transform a high-dimensional feature vector into a compact and expressive binary code through multiple mapping equations, has achieved great success in the field of fast image retrieval. In recent years, with the rapid development of deep convolutional neural networks, many hash algorithms based on convolutional neural networks have been proposed and have shown great prospects. In particular, due to the lack of existing labeled data and the manpower and material resources required to mark pictures, unsupervised hashing algorithms based on unlabeled data have received wide...

AI Technical Summary

Problems solved by technology

[0005] In view of the above-mentioned deficiencies in the prior art, the purpose of the present invention is to provide a convolutional neural network-based unsupervised hash fast image retrieval system and method to solve the problem of unbalanced training data and uncoordinated training in the existing methods. question

Images