Human Face Detection and Tracking using Skin Color Modeling and Connected Component Operators

Abstract

Face Recognition (FR) systems are increasingly gaining more importance. Face detection and tracking in a complex scene forms the first step in building a practical FR system. In this paper, a method to detect and track human faces in color image sequences is described. Skin color classification and morphological segmentation is used to detect face(s) in the first frame. These detected faces are tracked over subsequent frames by using the position of the faces in the first frame as the marker and detecting for skin in the localized region. Specific advantages of this approach are that skin color analysis method is simple and powerful, and the system can be used to detect/track multiple faces.

Indexing terms:

• Face detection/tracking
• Skin color modeling
• Connected component operators
• Structuring element

Additional information

Notes on contributors

Prem Kuchi

Prem Kuchi received his BE degree from Karnataka Regional Engineering College (KREC), Surathkal in 2001. He is presently pursuing his MS degree in the Dept. of Electrical Engineering at the Arizona State University, Tempe, and is also working as a research assistant in the Visual Computing and Communications Lab, ASU. He was a recipient of the Summer Research Fellowship awarded by the Jawaharlal Nehru Center for Advanced Scientific Research during Jul.-Sep. 2000. His present research interests include Image Processing, Pattern Recognition and Biometrics.

Prasad Gabbur

Prasad Gabbur received his BE degree from KREC, Surathkal in 2001. He is presently pursuing his MS degree in the Dept. of Electrical and Computer Engineering at the University of Arizona, Tucson and is a teaching assistant in the department. He was a Young Engineering research fellow of the Indian Institute of Science, Bangalore during Jul.-Sep. 2000. His research interests are in the fields of Signal and Image Processing, Pattern Recognition, and Computer Vision.

P Subbanna Bhat

P Subbanna Bhat obtained his BE and MTech degrees from KREC Surathkal in 1974 and 1977 respectively, and the PhD degree in Power Electronics from the Department of Electrical Engineering, IIT Kanpur in 1984. He is presently Professor and Head of the Dept. of E&C, KREC Surathkal. He was a Visiting Researcher at Dept. of Electrical Engineering, Huddersfield University, UK during 1995. His research interests are in the areas of Digital Signal Processing, Aritificial Neural Networks and Fuzzy logic.

S Sumam David

Sumam David S obtained her BTech degree from University of Kerala in 1985, and the MTech and PhD degrees from Department of Electrical Engineering, IIT Madras in 1986 and 1992 respectively. She is presently an Assistant Professor in the Dept of E&C, KREC Surathkal. She was a Visiting Researcher at Dept. of Computation, UMIST, Manchester, UK during 1995–96. She is a recipient of AICTE Career award for young teachers in 1998. Her research interests are in the areas of Audio-visual signal processing and VLSI for Signal processing.