Method of quick and accurate human face feature point positioning

Abstract

The invention elates to a human face character position method in the field of image processing technology. It first uses human face detecting method to find the human face area in the image, and then it detects eyes of human face area to fide the location of two eyes, then it according to the middle location of the two eyes, the distance between the two eyes and the angle of the two eyes to do imitate-injecting transformation to the initial ASM module so that the initial location of ASM module is near to the module which is formed by real character points, at last it dose ASM searching to the initial location after imitate-injecting transformation so as to obtain the location of human face character point.

Description

technical field [0001] The invention relates to a method in the technical field of image processing, in particular to a fast and accurate method for locating facial feature points. Background technique [0002] Facial feature point detection is the most critical key technology in applications such as face recognition, expression recognition, and gender recognition. The accuracy of feature point positioning directly affects the accuracy of recognition. Therefore, accurately locating a large number of facial feature points can greatly improve the accuracy of recognition. [0003] Although the existing local face feature point positioning method is fast, it can only give a few feature points, and it is not robust enough to meet the recognition requirements. Compared with the local face feature point positioning method, the active shape model (Active Shape Models, ASM) method can locate many face feature points at the same time, and the speed is fast, so it is widely used in fe...

AI Technical Summary

Problems solved by technology

But the ASM method is very sensitive to the initial position of the model: if the feature point position in the initial model is close to the actual feature point position, the ASM method will find all the feature points very quickly and accurately; but if the initial position is far from the actual feature point position, the ASM method Usually gives wrong positioning and cannot be used for identification at all

[0004] After searching the prior art documents, it was found that "Anil K. Jain Face Detection In Color images" (Rein K. Jain Face Detection In Color images) published by Rein-Lien Hsu et al. -Lien Hsu, MohamedAbdel-Mottaleb, Anil K.Jain Face Detection in Color Images, Institute of Electrical and Electronics Engineers, Pattern Analysis and Machine Learning VOL 24, N0.5.MAY 2002), was given by the statistics of a large number of samples According to the distribution of each component of the eye area in the YCbCr color space, and roughly locate the approximate position of the human eye and mouth according to the distribution of these components, but the number of feature points found by this type of method is too small to reach the human face. Identify the number of required feature points

Images