3D Face Recognition Method Based on Bayesian Multivariate Distribution Feature Extraction

Abstract

A 3D face recognition method based on Bayesian multivariate distribution feature extraction, including 3D data preprocessing, feature extraction and recognition classification. The advantages of the present invention are: to overcome the shortcomings of the large amount of calculation in the prior art, the present invention uses a three-dimensional face depth map for recognition, which can reduce the amount of calculation and improve the recognition efficiency; and solve the problem of insufficient training samples in the single-sample recognition problem , using the block method to increase the training samples; on this basis, a feature extraction method based on Bayesian analysis is proposed, so that the obtained features have the smallest intra-class distance and the largest inter-class distance, that is, the best separable and use the classification method based on the Mahalanobis distance to obtain the optimal recognition classification. Experimental data proves that the method of the present invention has better three-dimensional face recognition results.

Description

technical field [0001] The invention belongs to the technical field of biological feature recognition, and in particular relates to a new three-dimensional face recognition method based on Bayesian multivariate distribution feature extraction. Background technique [0002] Face recognition has gained enormous attention in the past few decades in both science and industry. Among them, two-dimensional face recognition technology has been widely studied. However, under the constraints of lighting conditions, poses, and representations, 2D face recognition remains a challenge. In this regard, the three-dimensional shape data of the face can be regarded as not changing with the change of illumination and view, and the accessories such as make-up have a great influence on the image but have no obvious influence on the three-dimensional data. Therefore, 3D face recognition is considered to have the characteristics of invariant illumination and pose invariance, which is more benef...

AI Technical Summary

Problems solved by technology

[0005] One of the main difficulties in 3D face recognition is that it is difficult to collect 3D face samples

Under the condition of a single training sample, due to the lack of training samples in the high-dimensional space, the recognition effect of the above method is not ideal

Therefore, for the single-sample recognition problem, the main challenge is the feature extraction of 3D faces.

Images