3D Face Recognition Based on Deep Learning

At present, face recognition is based on two-dimensional face database, Although the accuracy of face recognition is high, the influence of lighting, posture and expression on face recognition still exists. Because 3D face data not only has 2D face information, but also 3D face depth information. Reasonable use of depth information of 3D face can effectively reduce the impact of illumination, attitude and expression on face recognition. Therefore, this paper proposed a 3D face recognition method based on depth learning. Firstly, face image is preprocessed. Secondly, the output of the convolutional neural network is a abstract feature of the image, then, we fuse the abstract features of the 2D face abstract feature and the face depth map, and use the merged image as the input of the fully connected layer. Finally, the output of the fully connected layer is treated as the input of the classifier. Experimental data is two-dimensional face images and face depth maps which converted from 3D point clound data. The experimental results show that the recognition algorithm has strong robustness to the influence factors such as light, attitude and expression.

I. Introduction

The concept of face recognition originated in the 1960s, it is an important biometric recognition technology. Moreover, the face has the characteristics of highly non-rigid and has the advantages of directness, convenience, and good interactivity.