3-Dimensional object recognition by evolutional RBF network

Hideki Matsuda, Yasue Mitsukura, Minoru Fukumi, Norio Akamatsu

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

Abstract

This paper tries to recognize 3-dimensional objects by using an evolutional RBF network. Our proposed RBF network has the structure of preparing four RBFs for each hidden layer unit, selecting based on the Euclid distance between an input image and RBF. This structure can be invariant to 2- dimensional rotation by 90 degree. The other rotational invariance can be achieved by the RBF network. In hidden layer units, the number of RBFs, form, and arrangement are determined using real-coded GA. Computer simulations show object recognition can be done using such a method.

Original languageEnglish
Title of host publicationLecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
EditorsV. Palade, R.J. Howlett, L. Jain
Pages556-562
Number of pages7
Volume2773 PART 1
Publication statusPublished - 2003
Externally publishedYes
Event7th International Conference, KES 2003 - Oxford, United Kingdom
Duration: 2003 Sep 32003 Sep 5

Other

Other7th International Conference, KES 2003
CountryUnited Kingdom
CityOxford
Period03/9/303/9/5

Fingerprint

Radial basis function networks
Object recognition
Invariance
Computer simulation

ASJC Scopus subject areas

  • Hardware and Architecture

Cite this

Matsuda, H., Mitsukura, Y., Fukumi, M., & Akamatsu, N. (2003). 3-Dimensional object recognition by evolutional RBF network. In V. Palade, R. J. Howlett, & L. Jain (Eds.), Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 2773 PART 1, pp. 556-562)

3-Dimensional object recognition by evolutional RBF network. / Matsuda, Hideki; Mitsukura, Yasue; Fukumi, Minoru; Akamatsu, Norio.

Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science). ed. / V. Palade; R.J. Howlett; L. Jain. Vol. 2773 PART 1 2003. p. 556-562.

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

Matsuda, H, Mitsukura, Y, Fukumi, M & Akamatsu, N 2003, 3-Dimensional object recognition by evolutional RBF network. in V Palade, RJ Howlett & L Jain (eds), Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science). vol. 2773 PART 1, pp. 556-562, 7th International Conference, KES 2003, Oxford, United Kingdom, 03/9/3.
Matsuda H, Mitsukura Y, Fukumi M, Akamatsu N. 3-Dimensional object recognition by evolutional RBF network. In Palade V, Howlett RJ, Jain L, editors, Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science). Vol. 2773 PART 1. 2003. p. 556-562
Matsuda, Hideki ; Mitsukura, Yasue ; Fukumi, Minoru ; Akamatsu, Norio. / 3-Dimensional object recognition by evolutional RBF network. Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science). editor / V. Palade ; R.J. Howlett ; L. Jain. Vol. 2773 PART 1 2003. pp. 556-562
@inproceedings{beb61abdce0d4bd5a6b1e9f1fab3bbc5,
title = "3-Dimensional object recognition by evolutional RBF network",
abstract = "This paper tries to recognize 3-dimensional objects by using an evolutional RBF network. Our proposed RBF network has the structure of preparing four RBFs for each hidden layer unit, selecting based on the Euclid distance between an input image and RBF. This structure can be invariant to 2- dimensional rotation by 90 degree. The other rotational invariance can be achieved by the RBF network. In hidden layer units, the number of RBFs, form, and arrangement are determined using real-coded GA. Computer simulations show object recognition can be done using such a method.",
author = "Hideki Matsuda and Yasue Mitsukura and Minoru Fukumi and Norio Akamatsu",
year = "2003",
language = "English",
volume = "2773 PART 1",
pages = "556--562",
editor = "V. Palade and R.J. Howlett and L. Jain",
booktitle = "Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)",

}

TY - GEN

T1 - 3-Dimensional object recognition by evolutional RBF network

AU - Matsuda, Hideki

AU - Mitsukura, Yasue

AU - Fukumi, Minoru

AU - Akamatsu, Norio

PY - 2003

Y1 - 2003

N2 - This paper tries to recognize 3-dimensional objects by using an evolutional RBF network. Our proposed RBF network has the structure of preparing four RBFs for each hidden layer unit, selecting based on the Euclid distance between an input image and RBF. This structure can be invariant to 2- dimensional rotation by 90 degree. The other rotational invariance can be achieved by the RBF network. In hidden layer units, the number of RBFs, form, and arrangement are determined using real-coded GA. Computer simulations show object recognition can be done using such a method.

AB - This paper tries to recognize 3-dimensional objects by using an evolutional RBF network. Our proposed RBF network has the structure of preparing four RBFs for each hidden layer unit, selecting based on the Euclid distance between an input image and RBF. This structure can be invariant to 2- dimensional rotation by 90 degree. The other rotational invariance can be achieved by the RBF network. In hidden layer units, the number of RBFs, form, and arrangement are determined using real-coded GA. Computer simulations show object recognition can be done using such a method.

UR - http://www.scopus.com/inward/record.url?scp=8344269368&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=8344269368&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:8344269368

VL - 2773 PART 1

SP - 556

EP - 562

BT - Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)

A2 - Palade, V.

A2 - Howlett, R.J.

A2 - Jain, L.

ER -