Facial expression synthetic method based on rapid expression information extraction and Poisson image fusion

Abstract

The present invention discloses a facial expression synthetic method based on rapid expression information extraction and Poisson image fusion. The method mainly solves the problem in the prior art that the expression detail information can not be extracted rapidly and effectively and can not be synthesized to a target face, and comprises the realization steps of 1) obtaining a corresponding expression template according top the face characteristic point data; 2) according to an expression shape template of a target object, deforming a neutral expression image of the target object and a non-neutral expression image of a source object to the non-neutral expression shapes of the target object; 3) extracting the deformed expression detail information of a figure expression image block in a frequency domain; 4) using a Poisson image fusion method to filter the extracted expression details of the source object; 5) using the Poisson image fusion method to synthesize the filtered expression detail information to the deformation expression of the target object to thereby obtain a final synthesis result. The facial expression synthetic method of the present invention is small in needed sample capacity and natural and vivid in synthesis result, and can be used for the figure animation rendering, the video conference and the man-machine interaction.

Description

technical field [0001] The invention belongs to the fields of computer vision and computer graphics, in particular to a method for synthesizing human facial expressions. It can be used for character animation rendering, video conferencing and human-computer interaction. Background technique [0002] Facial expression is one of the external manifestations of internal subjective emotions, which has rich expressive power. Due to the diversity and complexity of facial expressions, facial expression synthesis must not only consider the overall movement and deformation of facial features, but also consider local subtle changes in expression textures. These expression details can often better reflect facial expression changes. , but these facial expression details are often difficult to obtain through expression simulation, and realistic expression details can be obtained through expression synthesis. How to extract the detailed texture of the expression from the complex expressi...

AI Technical Summary

Problems solved by technology

However, the processing methods based on the image domain are susceptible to the influence of illumination and noise, and the extracted expression information is not rich enough; in addition, these methods often require a neutral expression face image of the source object as a reference for extracting the detailed information of the expression. It is necessary to align the neutral and non-neutral expression images of the source object; and most of these methods achieve the fusion of the source object's expression details and the target object's facial features through simple weighting, resulting in a serious loss of expression details

For this reason, the facial expression effect synthesized by the above methods is often not significant enough, thereby affecting the visual fidelity of the image

Images