Face extraction from video sequences by K-means clustering and fusion

Face segmentation is an important processing step in a typically face-based person identification system. This paper presents a modified K-means clustering and fusion approach for face region extraction from colorful images of video sequences. It is based on L*a*b* color space analysis and consists of three processing steps: color number estimation, color region clustering, and face region post processing. Moreover, experimental results on CIPR public video sequences are also exhibited to verify the feasibility, high efficiency and accuracy.