Title :
Facial Caricaturing System Based on Multi-view Active Shape Models
Author :
Kamimura, Takuya ; Chen, Yen-wei
Author_Institution :
Grad. Sch. of Sci. & Eng., Rirsumeikan Univ., Kusatsu, Japan
Abstract :
In this paper, we proposed an automatic facial caricaturing system based on multi-view Active Shape Model (ASM). The ASM is used for automatic extraction of feature points. But it is difficult to apply the conventional ASM to facial images with pose variations. We developed a multi-view ASM bank, which includes various ASMs corresponding to each pose. The multi-view ASMs can extract feature points correctly not only for the fontal facial images but also for pose variations. Moreover, we developed an automatic facial caricaturing system. This system consists two parts: automatic extraction of feature points based on multi-view ASMs, and B-spline based caricaturing.
Keywords :
face recognition; feature extraction; facial caricaturing system; facial images; feature points extraction; multiview active shape models; pose variations; Active appearance model; Active shape model; Eigenvalues and eigenfunctions; Eyebrows; Face; Feature extraction; Humans; Principal component analysis; Spline; Visual effects; Active Shape Model; Principal Component Analysis; face recognition; pose robust;
Conference_Titel :
Natural Computation, 2009. ICNC '09. Fifth International Conference on
Conference_Location :
Tianjin
Print_ISBN :
978-0-7695-3736-8
DOI :
10.1109/ICNC.2009.656