Object Recognition in Image Sequences with Hopfield Neural Network

Kouichirou NISHIMURA; Masao IZUMI; Kunio FUKUNAGA

Object Recognition in Image Sequences with Hopfield Neural Network

Kouichirou NISHIMURA, Masao IZUMI, Kunio FUKUNAGA

Full Text Views

0

Cite this

Summary :

In case of object recognition using 3-D configuration data, the scale and poses of the object are important factors. If they are not known, we can not compare the object with the models in the database. Hence we propose a strategy for object recognition independently of its scale and poses, which is based on Hopfield neural network. And we also propose a strategy for estimation of the camera motion to reconstruct 3-D configuration of the object. In this strategy, the camera motion is estimated only with the sequential images taken by a moving camera. Consequently, the 3-D configuration of the object is reconstructed only with the sequential images. And we adopt the multiple regression analysis for estimation of the camera motion parameters so as to reduce the errors of them.

Publication: IEICE TRANSACTIONS on Information Vol.E78-D No.8 pp.1058-1064

Publication Date: 1995/08/25

Publicized

Online ISSN

DOI

Type of Manuscript: PAPER

Category: Image Processing, Computer Graphics and Pattern Recognition

Cite this

Copy

Kouichirou NISHIMURA, Masao IZUMI, Kunio FUKUNAGA, "Object Recognition in Image Sequences with Hopfield Neural Network" in IEICE TRANSACTIONS on Information, vol. E78-D, no. 8, pp. 1058-1064, August 1995, doi: .
Abstract: In case of object recognition using 3-D configuration data, the scale and poses of the object are important factors. If they are not known, we can not compare the object with the models in the database. Hence we propose a strategy for object recognition independently of its scale and poses, which is based on Hopfield neural network. And we also propose a strategy for estimation of the camera motion to reconstruct 3-D configuration of the object. In this strategy, the camera motion is estimated only with the sequential images taken by a moving camera. Consequently, the 3-D configuration of the object is reconstructed only with the sequential images. And we adopt the multiple regression analysis for estimation of the camera motion parameters so as to reduce the errors of them.
URL: https://global.ieice.org/en_transactions/information/10.1587/e78-d_8_1058/_p

Copy

@ARTICLE{e78-d_8_1058,
author={Kouichirou NISHIMURA, Masao IZUMI, Kunio FUKUNAGA, },
journal={IEICE TRANSACTIONS on Information},
title={Object Recognition in Image Sequences with Hopfield Neural Network},
year={1995},
volume={E78-D},
number={8},
pages={1058-1064},
abstract={In case of object recognition using 3-D configuration data, the scale and poses of the object are important factors. If they are not known, we can not compare the object with the models in the database. Hence we propose a strategy for object recognition independently of its scale and poses, which is based on Hopfield neural network. And we also propose a strategy for estimation of the camera motion to reconstruct 3-D configuration of the object. In this strategy, the camera motion is estimated only with the sequential images taken by a moving camera. Consequently, the 3-D configuration of the object is reconstructed only with the sequential images. And we adopt the multiple regression analysis for estimation of the camera motion parameters so as to reduce the errors of them.},
keywords={},
doi={},
ISSN={},
month={August},}

Copy

TY - JOUR
TI - Object Recognition in Image Sequences with Hopfield Neural Network
T2 - IEICE TRANSACTIONS on Information
SP - 1058
EP - 1064
AU - Kouichirou NISHIMURA
AU - Masao IZUMI
AU - Kunio FUKUNAGA
PY - 1995
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E78-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 1995
AB - In case of object recognition using 3-D configuration data, the scale and poses of the object are important factors. If they are not known, we can not compare the object with the models in the database. Hence we propose a strategy for object recognition independently of its scale and poses, which is based on Hopfield neural network. And we also propose a strategy for estimation of the camera motion to reconstruct 3-D configuration of the object. In this strategy, the camera motion is estimated only with the sequential images taken by a moving camera. Consequently, the 3-D configuration of the object is reconstructed only with the sequential images. And we adopt the multiple regression analysis for estimation of the camera motion parameters so as to reduce the errors of them.
ER -