A system for automatic generation of talking cartoon faces by facial image analysis, moving-lip synthesis, facial feature tracking, and voice synchronization techniques is proposed. A method for creating a personal cartoon face automatically is proposed first to extract facial features from a given neutral facial image. The method consists of the hierarchical bi-level thresholding and knowledge-based facial feature detection. A face model of 72 facial feature points is proposed then for personal cartoon face drawing and animation by a speech file and a script file.
Nine basic mouth shapes for Mandarin speaking are proposed to synthesize the moving lips. Cartoon faces can also be animated by the use of sequential facial images through automatic tracking of facial features.
Finally, an editable and opened vector-based XML language of W3C (World Wide Web Consortium) standard-SVG (Scalable Vector Graphics) is used for rendering cartoon faces and synchronizing their animations with speech. Good experimental results show the feasibility of the proposed methods.
Proceedings of 2004 Conference on Computer Vision, Graphics and Image Processing, Hualien, Taiwan, Republic of China