Self-learning face verification method

Abstract

The present invention discloses a self-learning face verification method. The method comprises the steps of: the step 101: employing a marked face sample set L to train a convolutional neural network;the step 102: employing the convolutional neural network to perform marking of an unmarked sample set U; the step 103: employing the sample set U to perform fine tuning of the convolutional neural network; the step 104: employing the sample set L to perform fine tuning of the convolutional neural network; and the step 105: repeatedly performing the steps 102, 103 and 104 for many times.

Description

technical field [0001] The invention relates to the field of biological feature recognition, in particular to a self-learning convolutional neural network training method applied to face verification. Background technique [0002] Face verification is a technology for identity confirmation based on human facial feature information. It has been widely used in identity authentication because of its security, friendliness and reliability. The important content of face verification research is how to obtain effective feature representation, maximize inter-class distance and minimize intra-class distance. Using traditional Gabor, LBP and other manually selected features is not enough to capture the essential features of the face and achieve high-precision face verification. In recent years, deep learning methods have been successfully applied to face verification. The deep learning method obtains rich face identity attribute information through training on large-scale real data...

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

Images