A standard face generation method based on a generative adversarial mechanism and an attention mechanism

Abstract

The invention discloses a standard face generation method based on a generative adversarial mechanism and an attention mechanism, and the method comprises the steps: a data set design step: building face codes with a plurality of non-limiting factors for a face image according to the related annotation data of a database, and enabling the codes and the face image to serve as the input of a model;A model design and training step: designing a corresponding network structure by utilizing a generative adversarial mechanism and an attention mechanism, and carrying out model training by utilizing the constructed data pair so as to obtain a network model weight; And a model prediction step: predicting the acquired face image through the model. According to the invention, a deep learning networktechnology is applied to standard face generation to generate color, forward and normal illumination standard face images; An accurate standard front face image can be obtained through a deep learningnetwork method, the matching difficulty of the standard front face image and data in a single sample database is reduced, and a solid foundation is laid for subsequent face feature extraction and single sample face recognition.

Description

technical field [0001] The invention relates to the technical field of deep learning applications, in particular to a standard face generation method based on a generation confrontation mechanism and an attention mechanism. Background technique [0002] In recent years, video surveillance has been popularized in large and medium-sized cities across the country, and has been widely used in the construction of social security prevention and control systems, and has become a powerful technical means for public security organs to investigate and solve crimes. Especially in mass incidents, major cases and double robbery cases, evidence clues obtained from video surveillance videos play a key role in the rapid detection of cases. At present, domestic public security organs mainly use video surveillance videos to search for criminal clues and criminal evidence after the event, and lock the suspect's identity by comparing the facial information of key suspects with the personnel inf...

AI Technical Summary

Problems solved by technology

However, there are many limiting factors in the face information of the suspect in the surveillance video, such as the interference of expression information, gesture interference or the interference of shooting light.

Since most of the personnel face information images in the database of the Public Security Bureau are only a sample of a single ID photo, the success rate is greatly restricted when the face images interfered with by the above-mentioned various restrictive factors are processed, which often leads to missed detection. and error detection

Images