An Image Anomaly Detection Method Based on Generative Adversarial Networks

Abstract

The invention discloses an image abnormality detection method based on a generative confrontation network, which comprehensively considers the characteristics of normal images and abnormal images, and generates abnormal images and detects abnormal images through a generative confrontation model. The steps include: obtaining a training data set and constructing Hidden space; Construct a generation network to obtain a set of generated pictures; Construct an encoding network to obtain a mapping of a set of generated pictures on an implicit space; Construct a shared parameter through a discrimination network and a detection network; The generation network, the encoding network , network discriminant network and detection network constitute a generative confrontation network and carry out confrontation training. The invention can make full use of the relationship between abnormal data and normal data to generate an adversarial network for detecting abnormal images, thereby effectively determining the boundaries of normal data and improving the accuracy of abnormal detection.

Description

technical field [0001] The invention relates to the field of anomaly detection, in particular to an image anomaly detection method based on generating confrontation networks. Background technique [0002] Anomaly detection in images refers to the classic problem of images that do not conform to expected normal classes. The characteristic of the data is that there are enough samples of abnormal images, and there are far more normal images in the existing data than abnormal samples. With the rapid development of technology and requirements, anomaly detection appears in different application areas, including security monitoring, traffic monitoring, medical image disease diagnosis and many other applications. [0003] The key to image anomaly detection is to model the distribution of normal and abnormal images, which are usually high-dimensional and complex. In recent years, generative adversarial models have shown promising results in modeling and synthesizing complex pattern...

AI Technical Summary

Problems solved by technology

However, all existing models focus on discovering normal patterns

Images