Scrambling face recognition method based on variable cascade information bottleneck

Abstract

The invention discloses a scrambling face recognition method based on a variable cascade information bottleneck. The method comprises the following steps: 1) preprocessing a training data set; 2) defining and initializing a model; 3) forward propagation of the data in batches; 4) calculating a loss function; 5) calculating a gradient through back propagation, and updating the weight; 6) performingiterative training, and repeatedly executing the steps 3) to 5) until the whole model converges; And 7) testing a model result, inputting the face image in the test set, and obtaining a final classification result through the whole model. According to the method, training is carried out under three data sets of ORL, CMUPIE and PUBFIG, testing is carried out on a test set, results are displayed under different scrambling operations, and the method can achieve the highest recognition accuracy.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a scrambled face recognition method based on variable cascading information bottlenecks. Background technique [0002] With the rapid development of the Internet, computer vision and camera equipment in recent years, intelligent video surveillance technology has become more and more widely used in many real-world scenarios. In many public places, the functions of intelligent video surveillance for real-time security and visual management are even more difficult to replace. However, technology is a double-edged sword. While video surveillance brings convenience to our life, it also brings privacy leakage. In many existing applications, especially when the police conduct criminal investigations, it is often necessary to obtain a large amount of video content containing private information. Similar applications include real-time monitoring systems for shopping malls. Thes...

AI Technical Summary

Problems solved by technology

These three types of methods are applicable to a certain extent, but they lack a unified modeling of scrambling face recognition methods. At the same time, it does not explain whether they are effective for various scrambling methods.

Images