A Face Recognition Method Combining Raw Data and Generated Data

Abstract

The invention provides a method for training a convolutional neural network through a small-scale human face data set, which is characterized in that it comprises steps: Step 1: using the original marked human face sample set to train a convolutional neural network VGG face recognition model; Step 2: Construct a deep convolutional generation confrontation network DCGAN model, and use the original labeled face sample set to train a deep convolutional generation confrontation network; Step 3: Generate an unlabeled face sample set through DCGAN; Step 4: Generate a human face with DCGAN Face dataset annotation; Step 5: Use the original labeled face sample set to train the plug-and-play generation network PPGN; Step 6: Generate a labeled face sample set through PPGN; Step 7: Combine the samples generated by DCGAN and PPGN Set and the original labeled sample set to train the convolutional neural network; Step 8: Repeat the training, that is, repeat steps 4, 5, 6, and 7 multiple times; Step 9, use the original labeled face sample set to fine-tune 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