An integrated face detection and recognition system

This paper presents an integrated approach to unconstrained face recognition in arbitrary scenes. The front end of the system comprises of a scale- and pose-tolerant face detector. Scale normalization is achieved through a novel combination of a skin color segmentation and log-polar mapping procedure. Principal component analysis is used with the multi-view approach proposed in [10] to handle the pose variations. For a given color input image, the detector encloses a face in a complex scene within a circular boundary and indicates the position of the nose. Next, for recognition, a radial grid mapping centered on the nose yields a feature vector within the circular boundary. As the width of the color segmented region provides an estimated size for the face, the extracted feature vector is scale-normalized by the estimated size. The feature vector is input to a trained neural network classifier for face identification. The system was evaluated using a database of 20 person's faces with varying scale and pose obtained on different complex backgrounds. The face detector was quite robust to all these variations. The performance of the face recognizer was also quite good except for sensitivity to small-scale face images. The integrated system achieved average recognition rates of 87% to 92%.

[1]  Rama Chellappa,et al.  Human and machine recognition of faces: a survey , 1995, Proc. IEEE.

[2]  Harry Wechsler,et al.  Detection of faces and facial landmarks using iconic filter banks , 1997, Pattern Recognit..

[3]  Monson H. Hayes,et al.  Face detection and recognition using hidden Markov models , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[4]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[5]  H. Araujo,et al.  An introduction to the log-polar mapping [image sampling] , 1996, Proceedings II Workshop on Cybernetic Vision.

[6]  A robust face identification against lighting fluctuation for lock control , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[7]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.

[8]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[9]  J. Dias,et al.  An Introduction to the Log-Polar Mapping , 1997 .

[10]  Takeo Kanade,et al.  Human Face Detection in Visual Scenes , 1995, NIPS.

[11]  Shaogang Gong,et al.  Segmentation and Tracking Using Color Mixture Models , 1998, ACCV.

[12]  Shaogang Gong,et al.  Face Recognition in Dynamic Scenes , 1997, BMVC.

[13]  Enrico Grosso,et al.  Active face recognition with a hybrid approach , 1997, Pattern Recognit. Lett..

[14]  Alex Pentland,et al.  Probabilistic Visual Learning for Object Representation , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Sun-Yuan Kung,et al.  Face recognition/detection by probabilistic decision-based neural network , 1997, IEEE Trans. Neural Networks.

[16]  Alex Pentland,et al.  View-based and modular eigenspaces for face recognition , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.