Invariant Object Recognition by Artificial Neural Network Using Fahlman and Lebiere's Learning Algorithm

Kazuki ITO; Masanori HAMAMOTO; Joarder KAMRUZZAMAN; Yukio KUMAGAI

Invariant Object Recognition by Artificial Neural Network Using Fahlman and Lebiere's Learning Algorithm

Kazuki ITO, Masanori HAMAMOTO, Joarder KAMRUZZAMAN, Yukio KUMAGAI

Full Text Views

0

Share
Cite this

Summary :

A new neural network system for object recognition is proposed which is invariant to translation, scaling and rotation. The system consists of two parts. The first is a preprocessor which obtains projection from the input image plane such that the projection features are translation and scale invariant, and then adopts the Rapid Transform which makes the transformed outputs rotation invariant. The second part is a neural net classifier which receives the outputs of preprocessing part as the input signals. The most attractive feature of this system is that, by using only a simple shift invariant transformation (Rapid transformation) in conjunction with the projection of the input image plane, invariancy is achieved and the system is of reasonably small size. Experiments with six geometrical objects with different degrees of scaling and rotation shows that the proposed system performs excellent when the neural net classifier is trained by the Cascade-correlation learning algorithm proposed by Fahlman and Lebiere.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E76-A No.7 pp.1267-1272

Publication Date: 1993/07/25

Publicized

Online ISSN

DOI

Type of Manuscript: LETTER

Category: Neural Networks

Cite this

Copy

Kazuki ITO, Masanori HAMAMOTO, Joarder KAMRUZZAMAN, Yukio KUMAGAI, "Invariant Object Recognition by Artificial Neural Network Using Fahlman and Lebiere's Learning Algorithm" in IEICE TRANSACTIONS on Fundamentals, vol. E76-A, no. 7, pp. 1267-1272, July 1993, doi: .
Abstract: A new neural network system for object recognition is proposed which is invariant to translation, scaling and rotation. The system consists of two parts. The first is a preprocessor which obtains projection from the input image plane such that the projection features are translation and scale invariant, and then adopts the Rapid Transform which makes the transformed outputs rotation invariant. The second part is a neural net classifier which receives the outputs of preprocessing part as the input signals. The most attractive feature of this system is that, by using only a simple shift invariant transformation (Rapid transformation) in conjunction with the projection of the input image plane, invariancy is achieved and the system is of reasonably small size. Experiments with six geometrical objects with different degrees of scaling and rotation shows that the proposed system performs excellent when the neural net classifier is trained by the Cascade-correlation learning algorithm proposed by Fahlman and Lebiere.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1587/e76-a_7_1267/_p

Copy

@ARTICLE{e76-a_7_1267,
author={Kazuki ITO, Masanori HAMAMOTO, Joarder KAMRUZZAMAN, Yukio KUMAGAI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Invariant Object Recognition by Artificial Neural Network Using Fahlman and Lebiere's Learning Algorithm},
year={1993},
volume={E76-A},
number={7},
pages={1267-1272},
abstract={A new neural network system for object recognition is proposed which is invariant to translation, scaling and rotation. The system consists of two parts. The first is a preprocessor which obtains projection from the input image plane such that the projection features are translation and scale invariant, and then adopts the Rapid Transform which makes the transformed outputs rotation invariant. The second part is a neural net classifier which receives the outputs of preprocessing part as the input signals. The most attractive feature of this system is that, by using only a simple shift invariant transformation (Rapid transformation) in conjunction with the projection of the input image plane, invariancy is achieved and the system is of reasonably small size. Experiments with six geometrical objects with different degrees of scaling and rotation shows that the proposed system performs excellent when the neural net classifier is trained by the Cascade-correlation learning algorithm proposed by Fahlman and Lebiere.},
keywords={},
doi={},
ISSN={},
month={July},}

Copy

TY - JOUR
TI - Invariant Object Recognition by Artificial Neural Network Using Fahlman and Lebiere's Learning Algorithm
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1267
EP - 1272
AU - Kazuki ITO
AU - Masanori HAMAMOTO
AU - Joarder KAMRUZZAMAN
AU - Yukio KUMAGAI
PY - 1993
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E76-A
IS - 7
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - July 1993
AB - A new neural network system for object recognition is proposed which is invariant to translation, scaling and rotation. The system consists of two parts. The first is a preprocessor which obtains projection from the input image plane such that the projection features are translation and scale invariant, and then adopts the Rapid Transform which makes the transformed outputs rotation invariant. The second part is a neural net classifier which receives the outputs of preprocessing part as the input signals. The most attractive feature of this system is that, by using only a simple shift invariant transformation (Rapid transformation) in conjunction with the projection of the input image plane, invariancy is achieved and the system is of reasonably small size. Experiments with six geometrical objects with different degrees of scaling and rotation shows that the proposed system performs excellent when the neural net classifier is trained by the Cascade-correlation learning algorithm proposed by Fahlman and Lebiere.
ER -