Method for learning non-linear face movement manifold based on statistical shape theory

Abstract

The invention discloses a method for learning a non-linear face movement manifold based on a statistical shape theory. A method for pre-processing face shape based on the statistical shape theory comprises the following steps of: (1) demeaning, normalizing and pluralizing the shape of each frame in a face movement sequence; (2) removing redundant information in complex representation; and (3) by combining Riemannian geometry tangent space mapping, projecting the face movement sequence of the complex representation into a tangent space of the movement manifold to form a face movement locus. Byusing a Gaussian process latent variable model, the method for learning the face movement manifold comprises the following steps of: (1) calculating a mean value and a covariance function of a Gaussian process, and determining a probability density function of the constructed Gaussian process; and (2) solving a latent variable by using a scaled conjugate gradient method to obtain a dimension reduction result which corresponds to the face movement locus. In the method, the dimension of face movement data is reduced by using a true manifold distance and using a good dimension reduction method, so that the structure of the face movement manifold is more accurately described.

Description

(1) Technical field: [0001] The present invention relates to a nonlinear facial motion manifold learning method based on statistical shape theory, especially the description of facial motion sequences in combination with Statistical Shape Theory and Gaussian Processing Latent Variable Models. It belongs to the field of image processing and pattern recognition. (two) background technology: [0002] How to endow machines with the ability to recognize facial movements and use facial movements as another input modality for machines, so as to assist machines in understanding human intentions and better serve human beings is the main task of facial analysis today. Facial analysis takes the face as the research object, and converts image and video information into pattern information that can be understood by machines. It is an important branch of the field of pattern recognition. Facial analysis has generally gone through two stages, namely: static image analysis and dynamic imag...

AI Technical Summary

Problems solved by technology

At present, although some nonlinear manifold learning methods are applied in facial analysis, most of them do not consider the characteristics of facial motion, and do not modify the method according to the needs of facial analysis.

Images