Visual nervous system based multi-module neural network for object recognition

Tetsuya Tannai, Masafumi Hagiwara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Although most of the conventional systems for object recognition have their own special targets, this paper gives a generic idea for universal object recognition method. The proposed multi-module neural network (MMNN) is a hierarchical network with cascade connections, and consists of several modules which can detect specific features. MMNN is constructed based on the information processing of the visual nervous system such as a column structure in the Visual Area I and the hierarchical hypothesis of Hubel-Wiesel. As an example of a target object, we deal with human faces detection in this paper. This system consists of several modules in parallel which are trained to respond selectively to human face components: the eyes, the nose, and the mouth. At last, the face area is detected by integrating the outputs of previous cell layer. We carried out a lot of experiments using 100 images having complex background to conform the effectiveness of the proposed scheme. 83% of faces are detected correctly.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Systems, Man and Cybernetics
Editors Anon
PublisherIEEE
Pages4284-4289
Number of pages6
Volume5
Publication statusPublished - 1998
EventProceedings of the 1998 IEEE International Conference on Systems, Man, and Cybernetics. Part 3 (of 5) - San Diego, CA, USA
Duration: 1998 Oct 111998 Oct 14

Other

OtherProceedings of the 1998 IEEE International Conference on Systems, Man, and Cybernetics. Part 3 (of 5)
CitySan Diego, CA, USA
Period98/10/1198/10/14

Fingerprint

Object recognition
Neurology
Cascade connections
Neural networks
Face recognition
Cells
Experiments

ASJC Scopus subject areas

  • Hardware and Architecture
  • Control and Systems Engineering

Cite this

Tannai, T., & Hagiwara, M. (1998). Visual nervous system based multi-module neural network for object recognition. In Anon (Ed.), Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (Vol. 5, pp. 4284-4289). IEEE.

Visual nervous system based multi-module neural network for object recognition. / Tannai, Tetsuya; Hagiwara, Masafumi.

Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. ed. / Anon. Vol. 5 IEEE, 1998. p. 4284-4289.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tannai, T & Hagiwara, M 1998, Visual nervous system based multi-module neural network for object recognition. in Anon (ed.), Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. vol. 5, IEEE, pp. 4284-4289, Proceedings of the 1998 IEEE International Conference on Systems, Man, and Cybernetics. Part 3 (of 5), San Diego, CA, USA, 98/10/11.
Tannai T, Hagiwara M. Visual nervous system based multi-module neural network for object recognition. In Anon, editor, Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 5. IEEE. 1998. p. 4284-4289
Tannai, Tetsuya ; Hagiwara, Masafumi. / Visual nervous system based multi-module neural network for object recognition. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. editor / Anon. Vol. 5 IEEE, 1998. pp. 4284-4289
@inproceedings{90c1fde31bac41259045d82c95dec3ab,
title = "Visual nervous system based multi-module neural network for object recognition",
abstract = "Although most of the conventional systems for object recognition have their own special targets, this paper gives a generic idea for universal object recognition method. The proposed multi-module neural network (MMNN) is a hierarchical network with cascade connections, and consists of several modules which can detect specific features. MMNN is constructed based on the information processing of the visual nervous system such as a column structure in the Visual Area I and the hierarchical hypothesis of Hubel-Wiesel. As an example of a target object, we deal with human faces detection in this paper. This system consists of several modules in parallel which are trained to respond selectively to human face components: the eyes, the nose, and the mouth. At last, the face area is detected by integrating the outputs of previous cell layer. We carried out a lot of experiments using 100 images having complex background to conform the effectiveness of the proposed scheme. 83{\%} of faces are detected correctly.",
author = "Tetsuya Tannai and Masafumi Hagiwara",
year = "1998",
language = "English",
volume = "5",
pages = "4284--4289",
editor = "Anon",
booktitle = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",
publisher = "IEEE",

}

TY - GEN

T1 - Visual nervous system based multi-module neural network for object recognition

AU - Tannai, Tetsuya

AU - Hagiwara, Masafumi

PY - 1998

Y1 - 1998

N2 - Although most of the conventional systems for object recognition have their own special targets, this paper gives a generic idea for universal object recognition method. The proposed multi-module neural network (MMNN) is a hierarchical network with cascade connections, and consists of several modules which can detect specific features. MMNN is constructed based on the information processing of the visual nervous system such as a column structure in the Visual Area I and the hierarchical hypothesis of Hubel-Wiesel. As an example of a target object, we deal with human faces detection in this paper. This system consists of several modules in parallel which are trained to respond selectively to human face components: the eyes, the nose, and the mouth. At last, the face area is detected by integrating the outputs of previous cell layer. We carried out a lot of experiments using 100 images having complex background to conform the effectiveness of the proposed scheme. 83% of faces are detected correctly.

AB - Although most of the conventional systems for object recognition have their own special targets, this paper gives a generic idea for universal object recognition method. The proposed multi-module neural network (MMNN) is a hierarchical network with cascade connections, and consists of several modules which can detect specific features. MMNN is constructed based on the information processing of the visual nervous system such as a column structure in the Visual Area I and the hierarchical hypothesis of Hubel-Wiesel. As an example of a target object, we deal with human faces detection in this paper. This system consists of several modules in parallel which are trained to respond selectively to human face components: the eyes, the nose, and the mouth. At last, the face area is detected by integrating the outputs of previous cell layer. We carried out a lot of experiments using 100 images having complex background to conform the effectiveness of the proposed scheme. 83% of faces are detected correctly.

UR - http://www.scopus.com/inward/record.url?scp=0032321342&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032321342&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0032321342

VL - 5

SP - 4284

EP - 4289

BT - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

A2 - Anon, null

PB - IEEE

ER -