Image retrieval method based on variable-length depth hash learning

Abstract

The invention discloses an image retrieval method based on variable-length depth hash learning and mainly relates to the field of image retrieval and depth learning. According to the method, learning of hash codes is modeled into the process of similarity learning. Specifically, the method utilizes a training image for generating a batch of ternary image sets. Each ternary image set comprises two images with the same label and one image with the different label. The purpose of model training is to space image pairs matched to the maximum and the unmatched image pairs in hamming space. The depth convolution nerve network is introduced into the learning part of the method, the image characteristics and hash functions are optimized in a combined mode, and the end-to-end training process is achieved; hash codes output by the convolution network have different weights. For the different retrieval task, a user can regular the length of the hash codes by disconnecting unimportant bits; meanwhile, according to the method, the discrimination of the hash codes can be kept effectively under the circumstance that the hash codes are short.

Description

technical field [0001] The present invention relates to the fields of image retrieval and deep learning, and more specifically, relates to an image retrieval method based on variable-length deep hash learning. Background technique [0002] With the rapid development of the Internet, the amount of multimedia information carried by images and videos has also shown explosive growth. How to obtain the information you want from massive amounts of data has become a widely discussed topic in industry and academia. Due to its huge advantages in storage space and computing efficiency, hashing technology has received extensive attention and research. With the deepening of research, hash learning based on image content focuses on converting images into binary codes and can still effectively maintain their semantic relevance with other images. In order to solve the above problems, many hash learning algorithms based on machine learning have been proposed. Among them, a class of image...

AI Technical Summary

Problems solved by technology

However, such methods are usually closely connected with well-designed feature spaces, and their retrieval accuracy will drop sharply as the number of hash codes decreases.

Images