Commonsense knowledge-based face detection

A. Z. Kouzani; F. He; K. Sammut

doi:10.1109/INES.1997.632419

Commonsense knowledge-based face detection

A. Z. Kouzani, F. He, K. Sammut

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

16 Citations (Scopus)

Abstract

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.

Original language	English
Title of host publication	Proceedings of IEEE International Conference on Intelligent Engineering Systems
Publisher	Institute of Electrical and Electronics Engineers
Pages	215-220
Number of pages	6
ISBN (Print)	0-7803-3627-5
DOIs	https://doi.org/10.1109/INES.1997.632419
Publication status	Published - 1997
Event	Proceedings of the 1997 International Conference on Intelligent Engineering Systems, INES - Budapest, Hungary Duration: 15 Sept 1997 → 17 Sept 1997

Conference

Conference	Proceedings of the 1997 International Conference on Intelligent Engineering Systems, INES
City	Budapest, Hungary
Period	15/09/97 → 17/09/97

Access to Document

10.1109/INES.1997.632419Licence: In Copyright

Cite this

@inproceedings{938c7987753248778a4fdc55f5e40237,

title = "Commonsense knowledge-based face detection",

abstract = "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.",

author = "Kouzani, {A. Z.} and F. He and K. Sammut",

year = "1997",

doi = "10.1109/INES.1997.632419",

language = "English",

isbn = "0-7803-3627-5",

pages = "215--220",

booktitle = "Proceedings of IEEE International Conference on Intelligent Engineering Systems",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "Proceedings of the 1997 International Conference on Intelligent Engineering Systems, INES ; Conference date: 15-09-1997 Through 17-09-1997",

}

Kouzani, AZ, He, F & Sammut, K 1997, Commonsense knowledge-based face detection. in Proceedings of IEEE International Conference on Intelligent Engineering Systems. Institute of Electrical and Electronics Engineers, pp. 215-220, Proceedings of the 1997 International Conference on Intelligent Engineering Systems, INES, Budapest, Hungary, 15/09/97. https://doi.org/10.1109/INES.1997.632419

TY - GEN

T1 - Commonsense knowledge-based face detection

AU - Kouzani, A. Z.

AU - He, F.

AU - Sammut, K.

PY - 1997

Y1 - 1997

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0031334757&partnerID=8YFLogxK

U2 - 10.1109/INES.1997.632419

DO - 10.1109/INES.1997.632419

M3 - Conference contribution

AN - SCOPUS:0031334757

SN - 0-7803-3627-5

SP - 215

EP - 220

BT - Proceedings of IEEE International Conference on Intelligent Engineering Systems

PB - Institute of Electrical and Electronics Engineers

T2 - Proceedings of the 1997 International Conference on Intelligent Engineering Systems, INES

Y2 - 15 September 1997 through 17 September 1997

ER -

Commonsense knowledge-based face detection

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this