A multi-scale Hash retrieval method based on deep learning

Abstract

Image pairing information and image classification information are optimized and a Hash code quantization process is used to realize a simple and easy end-to-end deep multi-scale supervision Hash method, and meanwhile design a brand new pyramid connected convolutional neural network structure, and the convolutional neural network structure takes paired images as training input and enables the output of each image to be approximate to a discrete Hash code. In addition, the feature map of each convolution layer is trained, feature fusion is carried out in the training process, and the performance of deep features is effectively improved. A neural network is constrained through a new binary constraint loss function based on end-to-end learning, and a Hash code with high feature representationcapability is obtained. High-quality multi-scale Hash codes are dynamically and directly learned through an end-to-end network, and the representation capability of the Hash codes in large-scale image retrieval is improved. Compared with an existing Hash method, the method has higher retrieval accuracy. Meanwhile, the network model is simple and flexible, can generate characteristics with strongrepresentation ability, and can be widely applied to other computer vision fields.

Description

technical field [0001] The invention relates to a multi-scale hash retrieval method based on deep learning, which belongs to the technical field of image and multimedia signal processing. Background technique [0002] In recent years, due to the explosive growth of the number of images on the Internet, fast and efficient retrieval of images has become increasingly important. Among many retrieval techniques, the hash-based retrieval method balances the efficiency and accuracy at the same time, which makes the retrieval achieve good results, and thus has received extensive attention. [0003] The hash-based retrieval method represents each picture with a binary code, which still approximately maintains the physical neighbor relationship in the picture space. Use the similarity criterion to calculate the similarity between the query picture and each image in the image feature library, and output the retrieval results under a given threshold after sorting according to the simil...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems of too long training time, too large quantization error, and information loss in the encoding process of hash retrieval based on deep learning, the present invention proposes a multi-scale hash retrieval method based on deep learning

Images