Automatic robust three-dimensional face detection method

Abstract

The invention discloses an automatic robust three-dimensional face detection method. According to the method, three-dimensional face discrete point cloud having plenty of redundancy information and noise under different attitudes and expressions are taken as input, and pre-processing, and three stages including nose tip point positioning and face detection are mainly included; for the pre-processing stage, smooth processing on an inputted point cloud model is firstly carried out, secondly, face pre-segmentation for the three-dimensional model is carried out; for the nose tip point positioning stage, firstly, initial face rotation transformation is carried out, and a discrete contour point set of an original face is acquired, secondly, curve fitting and gradient analysis are carried out, and a most-prominent point is extracted from a nose contour as a nose tip point; for the face detection stage, the nose tip point is a ball center, an empirical value is taken as a radius to segment to obtain a face region, and attitude correction is further carried out. The method is advantaged in that the method is applicable to a large-scale three-dimensional face database, good robustness for the attitudes and the expressions is realized, a processing speed is fast, and accuracy is high.

Description

technical field [0001] The invention belongs to the technical field of image processing and pattern recognition, and in particular relates to a face detection method suitable for three-dimensional face recognition. Background technique [0002] In the 21st century, mankind has entered the era of information explosion, and information security issues have become increasingly prominent. Identification and authentication have become urgent problems to be solved in various security systems. Biometric technology has become the most widely used identification and authentication technology due to its advantages of security and universal ease of maintenance. As a branch of biometric technology, face recognition is more and more used in practical applications due to its advantages of naturalness, friendliness, high user acceptance, and easy collection. Previous face recognition technologies are mostly based on two-dimensional images, which are easily affected by factors such as expr...

AI Technical Summary

Problems solved by technology

Application No. 200910197378.4, a patent titled "A Method for Fully Automatic 3D Face Detection and Pose Correction", which conducts multi-scale analysis on the surface of the face and locates the tip of the nose according to the regional characteristics of the nose, which is affected by the differences between faces , the regional characteristics of the nose are not stable, so the positioning results are often inaccurate

In 2013, Cai Yu of Jilin University's doctoral thesis "3D Face Detection and Recognition Technology" proposed to use statistical methods to analyze the curvature characteristics of the face to locate the tip of the nose to realize face detection, and the feature information such as curvature will be lost in the case of noise interference. very unstable

Application No. 201510064736.X, the patent titled "A 3D Face Feature Point Detection Method Resisting Expression, Posture and Occlusion Changes", proposes a method of training to generate an average nose model and locating the tip of the nose. This method needs to manually mark the face Marking points, the positioning process takes a long time

There are inevitable problems in the above methods, which cannot meet the speed and accuracy requirements of face detection at the same time, which restricts the development of 3D face recognition research.

Images