Deep hash method based on metric learning

Abstract

The invention discloses a deep hash method based on metric learning, relates to the field of computer vision and image processing, and solves the problems that a comparison loss function of an existing deep hash method can only enable feature vectors of images of the same category before quantization to be close as much as possible, but cannot encourage the same symbol; the values of different types of images before quantization are far away as far as possible, but the symbols cannot be encouraged to be opposite; finally, the quantized hash code is poor in discriminability, and misjudgment andother problems are caused. According to the invention, a hash comparison loss function is constructed; sign bit constraint is carried out on the real numerical value feature vector before quantization, so that the hash code of the representative image obtained after the real numerical value feature vector before quantization is quantized by a sign function is more accurate, and the sign is constrained through two control functions of fsim (fi.fj) and fdiff (fi.fj), other parts in the expression are used for enabling the feature values of the same category of images to be close and the featurevalues of different categories of images to be far. According to the method, the classification precision is effectively improved, and the misjudgment rate is reduced.

Description

technical field [0001] The invention relates to the fields of computer vision and image processing, in particular to a deep hashing method based on metric learning. Background technique [0002] With the advent of the information age, information technology and storage technology have been developed at a high speed, and massive data is generated every day, and the scale of image data is even more explosive. If large-scale data is directly searched by similarity, it will inevitably lead to serious problems. Big time and space overhead. At the same time, due to the complex structure of images and the high dimensionality of features, it is an urgent problem to ensure the retrieval accuracy and retrieval efficiency of image retrieval in large-scale data sets. [0003] The main process of the deep hashing method: first, a convolutional neural network is constructed based on the convolutional layer, pooling layer, etc. for feature extraction of images. Commonly used feature extra...

AI Technical Summary

Problems solved by technology

[0007] The present invention is to solve the contrast loss function of the existing deep hash method, which can only make the feature vectors of the images of the same category as close as possible before quantization, but cannot encourage their symbols to be the same; make the values ​​of different categories of images before quantization as possible Stay away, but it does not encourage its sign to be opposite; it will eventually lead to poor discrimination of the quantized hash code, causing misjudgment and other problems, providing a deep hash method based on metric learning

Images