Common-sense Knowledge Representation and Reasoning, and its Application to Face Detection
Abbas Z. Kouzani, Fangpo He, Karl Sammut
School of Engineering, Flinders University of SA, GPO Box 2100, Adelaide, SA 5001, Australia
Received:October 10, 1997Accepted:January 25, 1998Published:June 20, 1998
Keywords:Common-sense knowledge, Fuzzy logic, Neural networks, Face detection
This paper highlights the theory of common-sense knowledge in terms of representation and reasoning. A connectionist model is proposed for common-sense knowledge representation and reasoning. A generic fuzzy neuron is used as a basic element for the connectionist model. The representation and reasoning ability of the model are described through examples. A common-sense knowledge base is employed to develop a human face detection system. The system consists of three stages: preprocessing, face-components extraction, and final decision making. A neural-network-based algorithm is utilised to extract face components. Five networks are trained to detect the mouth, nose, eyes, and full face. The detected face components and their corresponding possibility degrees enable the knowledge base to locate faces in the image and to generate a membership degree for the detected faces within the face class. The experimental results obtained using this method are presented.
Cite this article as:A. Kouzani, F. He, and K. Sammut, “Common-sense Knowledge Representation and Reasoning, and its Application to Face Detection,” J. Adv. Comput. Intell. Intell. Inform., Vol.2 No.3, pp. 96-103, 1998.Data files: