Deakin University
Browse

Commonsense knowledge-based face detection

conference contribution
posted on 1997-12-01, 00:00 authored by Abbas KouzaniAbbas Kouzani, F He, K Sammut
A connectionist model is presented for commonsense knowledge representation and reasoning. The representation and reasoning ability of the model is described through examples. The commonsense 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 utilized to extract face components. Five networks are trained to detect mouth, nose, eyes, and full face. The detected face components and their corresponding possibility degrees allow the knowledge base to locate faces in the image and generate a membership degree for the detected faces within the face class. The experimental results obtained using this method are presented.

History

Pagination

215-220

Location

Budapest, Hungary

Start date

1997-09-17

End date

1997-09-17

Publication classification

EN.1 Other conference paper

Title of proceedings

IEEE International Conference on Intelligent Engineering Systems, Proceedings, INES

Publisher

IEEE

Place of publication

Piscataway, N.J.

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC