Three-dimensional transformation search method for extracting characteristic points in human face image

Abstract

The invention discloses a three-dimension transform search method for extracting characteristic point in face image which uses ASM (Active Shape Models) method locating face image as a base, changes two-dimension transform shape search method in present ASM into three-dimension transform shape search method. The method includes steps as follows: firstly, constructing a standard face three-dimension model; secondly, constructing three-dimension coordinates of a two-dimension stat model (basic shape) of ASM train centralizing face characteristic point according with standard face three-dimension model; finally, processing three-dimension transform to the two-dimension stat model having three-dimension coordinate and projecting to the two-dimension plane for approaching the given face characteristic point shape after search, wherein the search process adopts the method of two-step conversion and iterated approximation. The method can reflect real change of face gesture and has more search precision; the test result shows: the method can more approach fact characteristic point compared with present two-dimension transform search method.

Description

technical field [0001] The invention belongs to the field of face recognition, and in particular relates to a method for extracting feature points of facial organs of a face. Background technique [0002] Face recognition is a biometric identification technology based on human facial feature information, in which facial feature point extraction is the basis for face recognition. Face recognition as a way of identifying people has broad application prospects. At present, although some commercial face recognition systems are gradually entering the market, these technologies and systems are far from being practical, and their performance and accuracy are yet to come. improve. At present, the ASM (Active Shape Models, active shape model) positioning method is commonly used for facial feature point extraction, which generally includes three steps: (1) obtain a real shape description by aligning the training sample set; (2) capture Statistics of aligned shapes; (3) Search for sh...

AI Technical Summary

Problems solved by technology

This method has a good effect in the general frontal face positioning, but the effect is not good for the face positioning with a certain angle deflection

Through analysis and experiments, we found that this is related to the image search method: the current ASM method is to approximate the relevant shape by rotating, scaling and translating the basic shape of the two-dimensional image; and the human face is a three-dimensional object , the above operation obviously cannot fully reflect the change of face pose, therefore, there will be a large difference in the shape search approximation

Images