Face recognition method for combined original data and generated data

Abstract

The invention provides a method for training a convolution neural network through a small-scale face data set. The method is characterized by comprising the following steps: step one, using an originally marked face sample set to train a VGG face recognition model of the convolution neural network; step two, constructing a deep convolution to generate a DCGAN model of a confrontation network, andusing the originally marked face sample set to train the deep convolution so as to generate the confrontation network; step three, generating an unlabelled face sample set through DCGAN; step four, generating a face data set mark for the DCGAN; step five, using the originally marked face sample set to train a plug-and-play generated network PPGN; step six, generating a labeled face sample set through the PPGN; step seven, training the convolution neural network in combination with a DCGAN and PPGN generated sample set and the originally marked sample set; step eight, repeatedly training, namely repeating the step four, step five, step six and step seven repeatedly; and step nine, using the originally marked face sample set to finely adjust the VGG network.

Description

technical field [0001] The invention relates to the field of biological feature recognition, in particular to a method for training a face recognition neural network by simultaneously utilizing original label data and data generated by a generative confrontation network. Background technique [0002] Face recognition is a technology for identification based on human facial feature information. Because of its naturalness, non-mandatory and non-contact advantages, it has become a popular research field in computer vision. The key technology of face recognition is to effectively express the features of the face image, while the traditional manual selection of features such as SIFT and HOG is not enough to capture the essential features of the face. In recent years, the deep learning method has been successfully applied to the field of face recognition. By building a deep neural network to fit the face image, the essential expression of the face image features can be obtained, a...

AI Technical Summary

Problems solved by technology

[0003] However, the biggest problem with deep learning methods is that there are too many network parameters, and large-scale data labeling is required to achieve training, often requiring more than one million data. For example, FaceNet uses a large-scale 8 million people, a total of 200 million images

However, large-scale face data collection and labeling is a large consumption of human and financial resources.

Images