Human Face Detection System by Kenzan NET with preprocess analyzing hyperspectral image

Takakazu Chashikawa; Keizo Fujii; Yoshiyasu Takefuji

doi:10.1109/IPMM.1999.792522

Human Face Detection System by Kenzan NET with preprocess analyzing hyperspectral image

Takakazu Chashikawa, Keizo Fujii, Yoshiyasu Takefuji

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

Abstract

This paper proposes a neural network system to detect human faces. Our scheme is composed of a preprocess and KenzanNET. Preprocessing analyzes hyperspectral images by using a hybrid self-organizing classification model to extract skin area and making a facial candidate pattern based on the extracted skin area. KenzanNET discriminate a face from other body parts. KenzanNET is a kind of feed forward neural network and is made from CombNET [ I[ improved by an additional learning function. Under the various conditions in terms of background and brightness in a room and the distance between people and camera, our system can detect human face with 76.9% accuracy.

Original language	English
Title of host publication	Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999
Editors	Marcello M. Veiga, John A. Meech, Michael H. Smith, Steven R. LeClair
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	453-458
Number of pages	6
ISBN (Electronic)	0780354893, 9780780354890
DOIs	https://doi.org/10.1109/IPMM.1999.792522
Publication status	Published - 1999
Externally published	Yes
Event	2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999 - Honolulu, United States Duration: 1999 Jul 10 → 1999 Jul 15

Publication series

Name	Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999
Volume	1

Other

Other	2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999
Country/Territory	United States
City	Honolulu
Period	99/7/10 → 99/7/15

ASJC Scopus subject areas

Industrial and Manufacturing Engineering
Materials Science (miscellaneous)

Access to Document

10.1109/IPMM.1999.792522

Cite this

Chashikawa, T., Fujii, K., & Takefuji, Y. (1999). Human Face Detection System by Kenzan NET with preprocess analyzing hyperspectral image. In M. M. Veiga, J. A. Meech, M. H. Smith, & S. R. LeClair (Eds.), Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999 (pp. 453-458). [792522] (Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999; Vol. 1). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IPMM.1999.792522

Human Face Detection System by Kenzan NET with preprocess analyzing hyperspectral image. / Chashikawa, Takakazu; Fujii, Keizo; Takefuji, Yoshiyasu.
Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999. ed. / Marcello M. Veiga; John A. Meech; Michael H. Smith; Steven R. LeClair. Institute of Electrical and Electronics Engineers Inc., 1999. p. 453-458 792522 (Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999; Vol. 1).

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

Chashikawa, T, Fujii, K & Takefuji, Y 1999, Human Face Detection System by Kenzan NET with preprocess analyzing hyperspectral image. in MM Veiga, JA Meech, MH Smith & SR LeClair (eds), Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999., 792522, Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999, vol. 1, Institute of Electrical and Electronics Engineers Inc., pp. 453-458, 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999, Honolulu, United States, 99/7/10. https://doi.org/10.1109/IPMM.1999.792522

Chashikawa T, Fujii K, Takefuji Y. Human Face Detection System by Kenzan NET with preprocess analyzing hyperspectral image. In Veiga MM, Meech JA, Smith MH, LeClair SR, editors, Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999. Institute of Electrical and Electronics Engineers Inc. 1999. p. 453-458. 792522. (Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999). doi: 10.1109/IPMM.1999.792522

Chashikawa, Takakazu ; Fujii, Keizo ; Takefuji, Yoshiyasu. / Human Face Detection System by Kenzan NET with preprocess analyzing hyperspectral image. Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999. editor / Marcello M. Veiga ; John A. Meech ; Michael H. Smith ; Steven R. LeClair. Institute of Electrical and Electronics Engineers Inc., 1999. pp. 453-458 (Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999).

@inproceedings{b0f76ea125b24ce7a32afe064a62fafe,

title = "Human Face Detection System by Kenzan NET with preprocess analyzing hyperspectral image",

abstract = "This paper proposes a neural network system to detect human faces. Our scheme is composed of a preprocess and KenzanNET. Preprocessing analyzes hyperspectral images by using a hybrid self-organizing classification model to extract skin area and making a facial candidate pattern based on the extracted skin area. KenzanNET discriminate a face from other body parts. KenzanNET is a kind of feed forward neural network and is made from CombNET [ I[ improved by an additional learning function. Under the various conditions in terms of background and brightness in a room and the distance between people and camera, our system can detect human face with 76.9% accuracy.",

author = "Takakazu Chashikawa and Keizo Fujii and Yoshiyasu Takefuji",

note = "Publisher Copyright: {\textcopyright} 1999 IEEE.; 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999 ; Conference date: 10-07-1999 Through 15-07-1999",

year = "1999",

doi = "10.1109/IPMM.1999.792522",

language = "English",

series = "Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "453--458",

editor = "Veiga, {Marcello M.} and Meech, {John A.} and Smith, {Michael H.} and LeClair, {Steven R.}",

booktitle = "Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999",

}

TY - GEN

T1 - Human Face Detection System by Kenzan NET with preprocess analyzing hyperspectral image

AU - Chashikawa, Takakazu

AU - Fujii, Keizo

AU - Takefuji, Yoshiyasu

PY - 1999

Y1 - 1999

N2 - This paper proposes a neural network system to detect human faces. Our scheme is composed of a preprocess and KenzanNET. Preprocessing analyzes hyperspectral images by using a hybrid self-organizing classification model to extract skin area and making a facial candidate pattern based on the extracted skin area. KenzanNET discriminate a face from other body parts. KenzanNET is a kind of feed forward neural network and is made from CombNET [ I[ improved by an additional learning function. Under the various conditions in terms of background and brightness in a room and the distance between people and camera, our system can detect human face with 76.9% accuracy.

AB - This paper proposes a neural network system to detect human faces. Our scheme is composed of a preprocess and KenzanNET. Preprocessing analyzes hyperspectral images by using a hybrid self-organizing classification model to extract skin area and making a facial candidate pattern based on the extracted skin area. KenzanNET discriminate a face from other body parts. KenzanNET is a kind of feed forward neural network and is made from CombNET [ I[ improved by an additional learning function. Under the various conditions in terms of background and brightness in a room and the distance between people and camera, our system can detect human face with 76.9% accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85040015258&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040015258&partnerID=8YFLogxK

U2 - 10.1109/IPMM.1999.792522

DO - 10.1109/IPMM.1999.792522

M3 - Conference contribution

AN - SCOPUS:85040015258

T3 - Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999

SP - 453

EP - 458

BT - Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999

A2 - Veiga, Marcello M.

A2 - Meech, John A.

A2 - Smith, Michael H.

A2 - LeClair, Steven R.

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd International Conference on Intelligent Processing and Manufacturing of Materials, IPMM 1999

Y2 - 10 July 1999 through 15 July 1999

ER -

Human Face Detection System by Kenzan NET with preprocess analyzing hyperspectral image

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this