Human face verification method based on bilinear united CNN

Abstract

The invention discloses a human face verification method based on bilinear united convolutional nerve network. The human face verification method comprises steps of 1) using a human face image which is prepared in advance to perform convolutional nerve network (CNN) training, 2) using the human face image which is in a training set to perform bilinear CNN fine tuning, 3) inputting a human face image to be verified, segmenting the two images, extracting united characteristics outputted by the bilinear CNN, and 4) making an obtained vector go through self-encoding network training to obtain a final verification result. The human face verification method is based on the bilinear CNN, replaces two repeated inputs of an original bilinear nerve network with different human face verification input images, and brings forward a human face verification description factor. The human face description factor has robustness to illumination, shielding and posture change. Furthermore, the characteristic extracted by the bilinear CNN has a smaller dimensionality than the characteristic dimensionality of a common CNN fully connected layer, which reduces number of parameters, makes follow-up deep belief network training simple and improves accuracy of human face verification.

Description

technical field [0001] The present invention relates to the field of computer vision, and more specifically, relates to a face verification method based on a bilinear joint convolutional neural network (CNN). Background technique [0002] Face recognition can be said to be the most commonly used identity authentication method in people's daily life, and it is also one of the most popular pattern recognition research topics at present. Face recognition is to dynamically capture the face of a person through a camera connected to a computer, and at the same time compare and recognize the captured face with the face in the pre-recruited personnel inventory. Other biometric identification methods require the cooperation of human behavior, but face recognition does not require passive cooperation and can be used in some concealed occasions. It can be called the most friendly biometric authentication technology. Face verification is a sub-problem of face recognition. It solves the...

AI Technical Summary

Problems solved by technology

The above methods have achieved good results, but the existing CNN-based face verification research usually ignores the characteristics of the face verification task itself, and directly uses a single face image as a training sample to extract features, while two input face images The relationship clues are helpful to improve the recognition accuracy based on CNN

Images