Automatic Generation of Facial Expression Using Triangular Geometric Deformation

Abstract

This paper presents an image deformation algorithm and constructs an automatic facial expression generation systemto generate new facial expressions in neutral state. After the users input the face image in a neutral state into thesystem, the system separates the possible facial areas and the image background by skin color segmentation. It thenuses the morphological operation to remove noise and to capture the organs of facial expression, such as the eyes,mouth, eyebrow, and nose. The feature control points are labeled according to the feature points (FPs) defined byMPEG-4. After the designation of the deformation expression, the system also increases the image correction pointsbased on the obtained FP coordinates. The FPs are utilized as image deformation units by triangular segmentation.The triangle is split into two vectors. The triangle points are regarded as linear combinations of two vectors, and thecoefficients of the linear combinations correspond to the triangular vectors of the original image. Next, thecorresponding coordinates are obtained to complete the image correction by image interpolation technology togenerate the new expression. As for the proposed deformation algorithm, 10 additional correction points aregenerated in the positions corresponding to the FPs obtained according to MPEG-4. Obtaining the correction pointswithin a very short operation time is easy. Using a particular triangulation for deformation can extend the material areawithout narrowing the unwanted material area, thus saving the filling material operation in some areas.