Face living body recognition network training method and system and electronic equipment

Abstract

The invention provides a human face living body recognition network training method and system and electronic equipment. The method comprises the following steps: acquiring a preprocessed image; performing feature extraction on the image, detecting face features in the image, and obtaining a classification prediction result; calculating a corresponding loss function value by adopting an Am-softmax Loss function based on a classification prediction result; based on the loss function value, a gradient descent algorithm is adopted to reversely solve a gradient and update model parameters of the recognition network, so that the trained recognition network can establish an angle boundary between different samples, a large-angle interval supervision function is formed between the different samples, the difference between the samples can be greatly increased, and the recognition accuracy is improved. The inter-class distance is enhanced, so that the trained recognition network has higher recognition precision when facing various attack faces, the face living bodies are accurately distinguished, and the recognition accuracy is improved.

Description

technical field [0001] The present invention relates to the technical field of face recognition network, in particular to a face recognition network training method, system and electronic equipment. Background technique [0002] Face liveness detection (face anti-spoofing) is a method of applying computer image processing technology to deal with counterfeit face attacks. The purpose is to capture real faces and prevent damage caused by attacking face invasion. At present, face Attack methods can be roughly divided into several types: paper attack, screen attack and 3D mask attack, which can be further subdivided into more (such as A4 paper, poster, PC, Pad, etc.). There are slight differences in images between living and non-living faces, such as color texture, non-rigid motion deformation, etc. Early methods are based on these image features for feature design, and finally use machine learning classifiers for decision analysis. [0003] With the development of the Internet...

AI Technical Summary

Problems solved by technology

[0007] In order to overcome the problem of low accuracy of existing human face liveness detection, the present invention provides a human face liveness recognition network training method, system and electronic equipment

Images