A robust face detector under partial occlusion

This paper presents a robust face detector under partial occlusion. In recent years, the effectiveness of Support Vector Machine (SVM) to object detection is reported. However, conventional methods apply one kernel to global features. Therefore, those methods are not robust to occlusion because global features are influenced easily by noise or occlusion. To overcome this problem, SVM with local kernels is proposed. It is used to realize a robust face detector under partial occlusion. The robustness of the proposed method under partial occlusion is shown by using the occluded face images. The proposed method can detect the faces wearing sunglasses or scarf. It is also confirmed that the proposed method is superior to the conventional SVM with global kernel.

• Type: Conference
• Year: 2004
• Where: ICIP
• Authors: Kazuhiro Hotta
• Keywords: Conventional Svm, Faces Wearing Sunglasses, ICIP 2004, Image Processing, Occluded Face Images, Partial Occlusion, Robust Face Detector