Face Segmentation under Unconstrained Scenes

In this paper, an efficient approach by combining the novel wavelet-based feature template, the support vector machine (SVM) classifier, and the wavelet entropy filtering is presented to robustly detect and segment human face image under complex background. Moreover, a face detection measure (FDM) criterion based on the distance between the expected and the detected eye-mouth triangle circumscribed circle areas is introduced to validate the performance of precise face segmentation.

• Type: Conference
• Year: 2006
• Where: ICMCS
• Authors: Jing-Wein Wang
• Keywords: Face Detection Measure, Human Face Image, ICMCS 2006, Precise Face Segmentation