Face shape recognition method and equipment from stereo images

Abstract

A face model having outer and inner facial features is matched to that of first and second models. Each facial feature of the first and second models is represented by plurality of points that are adjusted for each matching outer and inner facial feature of the first and second models using 1) the corresponding epipolar constraint for the inner features of the first and second models. 2) Local grey-level structure of both outer and inner features of the first and second models. The matching and the adjusting are repeated, for each of the first and second models, until the points for each of the outer and inner facial features on the respective first and second models that are found to match that of the face model have a relative offset there between of not greater than a predetermined convergence tolerance. The inner facial features can include a pair of eyes, a nose and a mouth. The outer facial features can include a pair of eyebrows and a silhouette of the jaw, chin, and cheeks.

Description

Technical field [0001] The present invention is directed to facial recognition technology, and more specifically, it relates to identifying facial features by locating points on facial features using multiple images of the face. Background of the invention [0002] You can express three-dimensional objects in two dimensions. In fact, the use of two-dimensional views to express three-dimensional objects has advantages in object modeling and synthesis. In this type of two-dimensional representation, there is no need to clearly restore these three-dimensional features of the object, which avoids the difficulties encountered in three-dimensional-based methods. On the contrary, the conventional approach is to use a view-based model and use multiple two-dimensional view projections to represent the object. When more than one two-dimensional view is used to represent an object, a corresponding mapping in pixels is usually required between each of these two-dimensional views. Alternative...

AI Technical Summary

Problems solved by technology

The first question is about: Locating feature points on features of this object by using the training set of 2D views

Once the feature points of these features on the object are located, a second problem arises: establishing a base correspondence between two or more sets of feature points from a corresponding number of 2D views

Therefore, when using conventional ASM, the correspondence between the identified features of these different views is imprecise

Images