作者: Te-Feng Su , Chih-Hsueh Duan , Shu-Fan Wang , Yu-Tzu Lee , Shang-Hong Lai
DOI: 10.1007/S11265-013-0751-5
关键词:
摘要: In this paper, we propose an automatic facial expression exaggeration system, which consists of face detection, recognition, and components, for generating exaggerated views different expressions input video. addition, the parallelized algorithms system are developed to reduce execution time on a multi-core embedded system. The experimental results show satisfactory computational efficiency under cluttered environments. quantitative comparisons that proposed parallelization strategies provide significant speedup compared single-processor implementation platform.