A compact Hash code learning method based on semantic protection

Abstract

The invention provides a compact Hash code learning method based on semantic protection, and the method comprises the steps: dividing a data set, and obtaining a test sample set, a training sample set, and an image library; then constructing a deep Hash network model; adding a hidden layer (Hash layer) to the last full connection layer of a common convolutional neural network model, the number ofneurons of the hidden layer is the length of Hash codes, an activation function is a panh function, designing a constraint function, protecting the semantic similarity of images, and meanwhile it is guaranteed that the learned Hash codes are evenly distributed and the quantization error is small; extracting Hash codes of the query image and the database image through the trained model, and calculating Hamming distances between the Hash codes of the image and the Hash codes of all the images in the database; and finally, sorting the Hash codes in the database according to a sequence of distances from small to large, and sequentially outputting the original images corresponding to the Hash codes to obtain a similar image retrieval result. According to the method, retrieval of large-scale images is more accurate and effective.

Description

technical field [0001] The invention belongs to the technical field of image retrieval, and in particular relates to a compact hash code learning method based on semantic protection, which is suitable for large-scale image retrieval tasks. Background technique [0002] With the rapid development of information technologies such as the Internet, cloud computing, and the Internet of Things, and the popularity of mobile digital media devices, people can produce, share, and disseminate various information anytime and anywhere, and images have become one of the important media for people to obtain information. influence and change people's lives. Commercial applications based on image retrieval technology also emerge in endlessly, such as Baidu image recognition, Taobao image, Google engine, etc. However, massive images bring certain difficulties to the management and analysis of data, such as high image feature dimension, large storage capacity, slow retrieval speed, etc., whic...

AI Technical Summary

Problems solved by technology

HashNet provides a new idea to reduce the quantization error, directly learns the binary code, reduces the step-by-step quantization error, but does not consider the uniform distribution of the binary code and other issues

Images