Adaptive Skin Color Model Switching for Face Tracking under Varying Illumination
Innovative Computing, Information and Control（2009）
摘要
In this paper, an adaptive skin color model switching based on AdaBoost method for face tracking is proposed. Possible skin clusters under illumination varying scenes are detected by an optimal skin color model, which is adaptively selected by a well-defined quality measure. The possible facial candidates are further validated by AdaBoost to determine whether human faces exist in video sequences or not. The tracking sequences reveal that good and robust results are obtained from dim-to profile-to back-light scenarios. The performance of the proposed method can achieve an average tracking time of about 145.4 ms/frame and a detection rate of 94.4%.
更多查看译文
关键词
face tracking sequence,average tracking time,skin clusters,video sequences,learning (artificial intelligence),varying illumination,possible facial candidate,adaptive skin color model switching,illumination varying scene detection,tracking,image sequences,possible skin cluster,tracking sequence,detection rate,optimal skin color model,adaboost method,adaptive skin color model,face tracking,image colour analysis,lighting,color,face,learning artificial intelligence,skin,pixel
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要