Face Detection and Modeling for Recognition

Face Detection and Modeling for Recognition By Rein-Lien Hsu Face recognition has received substantial attention from researchers in biometrics, computer vision, pattern recognition, and cognitive psychology communities because of the increased attention being devoted to security, man-machine communication, content-based image retrieval, and image/video coding. We have proposed two automated recognition paradigms to advance face recognition technology. Three major tasks involved in face recognition systems are: (i) face detection, (ii) face modeling, and (iii) face matching. We have developed a face detection algorithm for color images in the presence of various lighting conditions as well as complex backgrounds. Our detection method first corrects the color bias by a lighting compensation technique that automatically estimates the parameters of reference white for color correction. We overcame the difficulty of detecting the low-luma and high-luma skin tones by applying a nonlinear transformation to the Y CbCr color space. Our method generates face candidates based on the spatial arrangement of detected skin patches. We constructed eye, mouth, and face boundary maps to verify each face candidate. Experimental results demonstrate successful detection of faces with different sizes, color, position, scale, orientation, 3D pose, and expression in several photo collections. 3D human face models augment the appearance-based face recognition approaches to assist face recognition under the illumination and head pose variations. For the two proposed recognition paradigms, we have designed two methods for modeling human faces based on (i) a generic 3D face model and an individual’s facial measurements of shape and texture captured in the frontal view, and (ii) alignment of a semantic face graph, derived from a generic 3D face model, onto a frontal face image. Our modeling methods adapt recognition-oriented facial features of a generic model to those extracted from facial measurements in a global-to-local fashion. The first modeling method uses displacement propagation and 2.5D snakes for model alignment. The resulting 3D face model is visually similar to the true face, and proves to be quite useful for recognizing non-frontal views based on an appearance-based recognition algorithm. The second modeling method uses interacting snakes for graph alignment. A successful interaction of snakes (associated with eyes, mouth, nose, etc.) results in appropriate component weights based on distinctiveness and visibility of individual facial components. After alignment, facial components are transformed to a feature space and weighted for semantic face matching. The semantic face graph facilitates face matching based on selected components, and effective 3D model updating based on 2D images. The results of face matching demonstrate that the proposed model can lead to classification and visualization (e.g., the generation of cartoon faces and facial caricatures) of human faces using the derived semantic face graphs. c © Copyright 2002 by Rein-Lien Hsu All Rights Reserved To my parents; my lovely wife, Pei-Jing; and my son, Alan