MULTI-VIEW FACE DETECTION BASED ON KERNEL PRINCIPAL COMPONENT ANALYSIS AND KERNEL SUPPORT VECTOR TECHNIQUES

Detecting faces across multiple views is more challenging than in a frontal view. To address this problem,an efficient approach is presented in this paper using a kernel machine based approach for learning suchnonlinear mappings to provide effective view-based representation for multi-view face detection. In thispaper Kernel Principal Component Analysis (KPCA) is used to project data into the view-subspaces thencomputed as view-based features. Multi-view face detection is performed by classifying each input imageinto face or non-face class, by using a two class Kernel Support Vector Classifier (KSVC). Experimentalresults demonstrate successful face detection over a wide range of facial variation in color, illuminationconditions, position, scale, orientation, 3D pose, and expression in images from several photo collections.