Human Face Segmentation and Identification

This thesis considers segmentation and identiication of human faces from grey scale images with clutter. The segmentation developed utilizes the elliptical structure of the human head. It uses the information present in the edge map of the image and through some preprocessing separates the head from the background clutter. An ellipse is then tted to mark the boundary between the head region and the background. The identiication procedure nds feature points in the segmented face through a Gabor wavelet decomposition and performs graph matching. The segmentation and identiication algorithms were tested on a database of 48 images of 16 persons with encouraging results. Dedication To my grandmother Masooda Begum and my parents Iftikhar A. Sirohey and Zarina Sirohey ii Acknowledgements I would like to take this opportunity to thank all the people who have been instrumental the accomplishment of this task. First of all Professor Rama Chellappa, with his superb guidance and support during the course of this thesis. Dr. Q. Zheng for his time and eeort and the lively discussions that we had concerning the topic. and David for putting up with me for the last year. Our discussions together brought new insight for me regarding the research. And of course this work would not have been possible if not for the undying love, support and encouragement of my parents, Iftikhar A. Sirohey and Zarina Sirohey. To them any gratitude I may express will not be enough.

[1]  金出 武雄,et al.  Picture processing system by computer complex and recognition of human faces , 1974 .

[2]  Roberto Brunelli,et al.  Face Recognition through Geometrical Features , 1992, ECCV.

[3]  Stephen D. Shapiro,et al.  Feature space transforms for curve detection , 1978, Pattern Recognition.

[4]  Gaile G. Gordon,et al.  Application of morphology to feature extraction for face recognition , 1992, Electronic Imaging.

[5]  Rama Chellappa,et al.  A feature based approach to face recognition , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  Ian Craw,et al.  Finding Face Features , 1992, ECCV.

[7]  Yehezkel Yeshurun,et al.  Robust detection of facial features by generalized symmetry , 1992, [1992] Proceedings. 11th IAPR International Conference on Pattern Recognition.

[8]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Shimon Edelman,et al.  Learning to Recognize Faces from Examples , 1992, ECCV.

[10]  Venu Govindaraju,et al.  A computational model for face location , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[11]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[12]  Larry S. Davis,et al.  Labeling of human face components from range data , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.