Recognition of Line Shapes Using Neural Networks
Summary :
We apply neural networks to implement a line shape recognition/classification system. The purpose of employing neural networks is to eliminate target-specific algorithms from the system and to simplify the system. The system needs only to be trained by samples. The shapes are captured by the following operations. Lines to be processed are segmented at inflection points. Each segment is extended from both ends of it in a certain percentage. The shape of each extended segment is captured as an approximate curvature. Curvature sequence is normalized by size in order to get a scale-invariant measure. Feeding this normalized curvature date to a neural network leads to position-, rotation-, and scale-invariant line shape recognition. According to our experiments, almost 100% recognition rates are achieved against 5% random modification and 50%-200% scaling. The experimental results show that our method is effective. In addition, since this method captures shape locally, partial lines (caused by overlapping etc.) can also be recognized.
- Publication
- IEICE TRANSACTIONS on Information Vol.E77-D No.7 pp.754-760
- Publication Date
- 1994/07/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Special Section PAPER (Special Issue on Document Analysis and Recognition)
- Category
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Masaji KATAGIRI, Masakazu NAGURA, "Recognition of Line Shapes Using Neural Networks" in IEICE TRANSACTIONS on Information,
vol. E77-D, no. 7, pp. 754-760, July 1994, doi: .
Abstract: We apply neural networks to implement a line shape recognition/classification system. The purpose of employing neural networks is to eliminate target-specific algorithms from the system and to simplify the system. The system needs only to be trained by samples. The shapes are captured by the following operations. Lines to be processed are segmented at inflection points. Each segment is extended from both ends of it in a certain percentage. The shape of each extended segment is captured as an approximate curvature. Curvature sequence is normalized by size in order to get a scale-invariant measure. Feeding this normalized curvature date to a neural network leads to position-, rotation-, and scale-invariant line shape recognition. According to our experiments, almost 100% recognition rates are achieved against 5% random modification and 50%-200% scaling. The experimental results show that our method is effective. In addition, since this method captures shape locally, partial lines (caused by overlapping etc.) can also be recognized.
URL: https://global.ieice.org/en_transactions/information/10.1587/e77-d_7_754/_p
Copy
@ARTICLE{e77-d_7_754,
author={Masaji KATAGIRI, Masakazu NAGURA, },
journal={IEICE TRANSACTIONS on Information},
title={Recognition of Line Shapes Using Neural Networks},
year={1994},
volume={E77-D},
number={7},
pages={754-760},
abstract={We apply neural networks to implement a line shape recognition/classification system. The purpose of employing neural networks is to eliminate target-specific algorithms from the system and to simplify the system. The system needs only to be trained by samples. The shapes are captured by the following operations. Lines to be processed are segmented at inflection points. Each segment is extended from both ends of it in a certain percentage. The shape of each extended segment is captured as an approximate curvature. Curvature sequence is normalized by size in order to get a scale-invariant measure. Feeding this normalized curvature date to a neural network leads to position-, rotation-, and scale-invariant line shape recognition. According to our experiments, almost 100% recognition rates are achieved against 5% random modification and 50%-200% scaling. The experimental results show that our method is effective. In addition, since this method captures shape locally, partial lines (caused by overlapping etc.) can also be recognized.},
keywords={},
doi={},
ISSN={},
month={July},}
Copy
TY - JOUR
TI - Recognition of Line Shapes Using Neural Networks
T2 - IEICE TRANSACTIONS on Information
SP - 754
EP - 760
AU - Masaji KATAGIRI
AU - Masakazu NAGURA
PY - 1994
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E77-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 1994
AB - We apply neural networks to implement a line shape recognition/classification system. The purpose of employing neural networks is to eliminate target-specific algorithms from the system and to simplify the system. The system needs only to be trained by samples. The shapes are captured by the following operations. Lines to be processed are segmented at inflection points. Each segment is extended from both ends of it in a certain percentage. The shape of each extended segment is captured as an approximate curvature. Curvature sequence is normalized by size in order to get a scale-invariant measure. Feeding this normalized curvature date to a neural network leads to position-, rotation-, and scale-invariant line shape recognition. According to our experiments, almost 100% recognition rates are achieved against 5% random modification and 50%-200% scaling. The experimental results show that our method is effective. In addition, since this method captures shape locally, partial lines (caused by overlapping etc.) can also be recognized.
ER -
English
