A new approach for automated parts recognition using time series analysis and neural networks

Young Hae Lee, Seungki Moon, Hong Chul Lee

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

This paper presents a new approach for automated parts recognition. It is based on the use of the signature and autocorrelation functions for feature extraction and a neural network for the analysis of recognition. The signature represents the shapes of boundaries detected in digitized binary images of the parts. The autocorrelation coefficients computed from the signature are invariant to transformations such as scaling, translation and rotation of the parts. These unique extracted features are fed to the neural network. A multilayer perceptron with two hidden layers, along with a backpropagation learning algorithm, is used as a pattern classifier. In addition, the position information of the part for a robot with a vision system is described to permit grasping and pick-up. Experimental results indicate that the proposed approach is appropriate for the accurate and fast recognition and inspection of parts in automated manufacturing systems.

Original languageEnglish
Pages (from-to)167-175
Number of pages9
JournalJournal of Intelligent Manufacturing
Volume8
Issue number3
Publication statusPublished - 1997 Dec 1

Fingerprint

Time series analysis
Autocorrelation
Neural networks
Binary images
Backpropagation algorithms
Multilayer neural networks
Learning algorithms
Feature extraction
Classifiers
Inspection
Robots

Keywords

  • Feature extraction
  • Neural networks
  • Pattern recognition
  • Time series

ASJC Scopus subject areas

  • Artificial Intelligence
  • Industrial and Manufacturing Engineering

Cite this

A new approach for automated parts recognition using time series analysis and neural networks. / Lee, Young Hae; Moon, Seungki; Lee, Hong Chul.

In: Journal of Intelligent Manufacturing, Vol. 8, No. 3, 01.12.1997, p. 167-175.

Research output: Contribution to journalArticle

@article{cb5412bf58ce45f7a913560b0da04c7d,
title = "A new approach for automated parts recognition using time series analysis and neural networks",
abstract = "This paper presents a new approach for automated parts recognition. It is based on the use of the signature and autocorrelation functions for feature extraction and a neural network for the analysis of recognition. The signature represents the shapes of boundaries detected in digitized binary images of the parts. The autocorrelation coefficients computed from the signature are invariant to transformations such as scaling, translation and rotation of the parts. These unique extracted features are fed to the neural network. A multilayer perceptron with two hidden layers, along with a backpropagation learning algorithm, is used as a pattern classifier. In addition, the position information of the part for a robot with a vision system is described to permit grasping and pick-up. Experimental results indicate that the proposed approach is appropriate for the accurate and fast recognition and inspection of parts in automated manufacturing systems.",
keywords = "Feature extraction, Neural networks, Pattern recognition, Time series",
author = "Lee, {Young Hae} and Seungki Moon and Lee, {Hong Chul}",
year = "1997",
month = "12",
day = "1",
language = "English",
volume = "8",
pages = "167--175",
journal = "Journal of Intelligent Manufacturing",
issn = "0956-5515",
publisher = "Springer Netherlands",
number = "3",

}

TY - JOUR

T1 - A new approach for automated parts recognition using time series analysis and neural networks

AU - Lee, Young Hae

AU - Moon, Seungki

AU - Lee, Hong Chul

PY - 1997/12/1

Y1 - 1997/12/1

N2 - This paper presents a new approach for automated parts recognition. It is based on the use of the signature and autocorrelation functions for feature extraction and a neural network for the analysis of recognition. The signature represents the shapes of boundaries detected in digitized binary images of the parts. The autocorrelation coefficients computed from the signature are invariant to transformations such as scaling, translation and rotation of the parts. These unique extracted features are fed to the neural network. A multilayer perceptron with two hidden layers, along with a backpropagation learning algorithm, is used as a pattern classifier. In addition, the position information of the part for a robot with a vision system is described to permit grasping and pick-up. Experimental results indicate that the proposed approach is appropriate for the accurate and fast recognition and inspection of parts in automated manufacturing systems.

AB - This paper presents a new approach for automated parts recognition. It is based on the use of the signature and autocorrelation functions for feature extraction and a neural network for the analysis of recognition. The signature represents the shapes of boundaries detected in digitized binary images of the parts. The autocorrelation coefficients computed from the signature are invariant to transformations such as scaling, translation and rotation of the parts. These unique extracted features are fed to the neural network. A multilayer perceptron with two hidden layers, along with a backpropagation learning algorithm, is used as a pattern classifier. In addition, the position information of the part for a robot with a vision system is described to permit grasping and pick-up. Experimental results indicate that the proposed approach is appropriate for the accurate and fast recognition and inspection of parts in automated manufacturing systems.

KW - Feature extraction

KW - Neural networks

KW - Pattern recognition

KW - Time series

UR - http://www.scopus.com/inward/record.url?scp=0031169384&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031169384&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0031169384

VL - 8

SP - 167

EP - 175

JO - Journal of Intelligent Manufacturing

JF - Journal of Intelligent Manufacturing

SN - 0956-5515

IS - 3

ER -