A structural model for shape recognition using neural nets

Jose Antonio Ventura, Jen Ming Chen

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Shape representation and recognition is an important topic in many applications of computer vision and artificial intelligence, including character recognition, pattern recognition, machine monitoring, robot manipulation and production part recognition. In this paper, a structural model based on boundary information is proposed to describe the silhouette of planar objects (especially machined parts). The structural model describes objects by a set of primitives, each of which is represented by three geometric features: its length, curvature, and relative orientation. This representation scheme not only compresses the data, but also provides a compact and meaningful form to facilitate further recognition operations. Based on this model, the object recognition is accomplished by using a multilayered feedforward neural network. The proposed model is transformation invariant, which offers the necessary flexibility for real-time implementation in automated manufacturing systems. In addition, the numerical results for a set of ten reference shapes indicate that the matching engine can achieve very high success rates using short recognition times.

Original languageEnglish (US)
Pages (from-to)1-11
Number of pages11
JournalJournal of Intelligent Manufacturing
Volume7
Issue number1
DOIs
StatePublished - Jan 1 1996

Fingerprint

Neural networks
Character recognition
Feedforward neural networks
Object recognition
Computer vision
Pattern recognition
Artificial intelligence
Robots
Engines
Monitoring

All Science Journal Classification (ASJC) codes

  • Software
  • Industrial and Manufacturing Engineering
  • Artificial Intelligence

Cite this

@article{094ac32e992e42c5b00c5430fb03628e,
title = "A structural model for shape recognition using neural nets",
abstract = "Shape representation and recognition is an important topic in many applications of computer vision and artificial intelligence, including character recognition, pattern recognition, machine monitoring, robot manipulation and production part recognition. In this paper, a structural model based on boundary information is proposed to describe the silhouette of planar objects (especially machined parts). The structural model describes objects by a set of primitives, each of which is represented by three geometric features: its length, curvature, and relative orientation. This representation scheme not only compresses the data, but also provides a compact and meaningful form to facilitate further recognition operations. Based on this model, the object recognition is accomplished by using a multilayered feedforward neural network. The proposed model is transformation invariant, which offers the necessary flexibility for real-time implementation in automated manufacturing systems. In addition, the numerical results for a set of ten reference shapes indicate that the matching engine can achieve very high success rates using short recognition times.",
author = "Ventura, {Jose Antonio} and Chen, {Jen Ming}",
year = "1996",
month = "1",
day = "1",
doi = "10.1007/BF00114134",
language = "English (US)",
volume = "7",
pages = "1--11",
journal = "Journal of Intelligent Manufacturing",
issn = "0956-5515",
publisher = "Springer Netherlands",
number = "1",

}

A structural model for shape recognition using neural nets. / Ventura, Jose Antonio; Chen, Jen Ming.

In: Journal of Intelligent Manufacturing, Vol. 7, No. 1, 01.01.1996, p. 1-11.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A structural model for shape recognition using neural nets

AU - Ventura, Jose Antonio

AU - Chen, Jen Ming

PY - 1996/1/1

Y1 - 1996/1/1

N2 - Shape representation and recognition is an important topic in many applications of computer vision and artificial intelligence, including character recognition, pattern recognition, machine monitoring, robot manipulation and production part recognition. In this paper, a structural model based on boundary information is proposed to describe the silhouette of planar objects (especially machined parts). The structural model describes objects by a set of primitives, each of which is represented by three geometric features: its length, curvature, and relative orientation. This representation scheme not only compresses the data, but also provides a compact and meaningful form to facilitate further recognition operations. Based on this model, the object recognition is accomplished by using a multilayered feedforward neural network. The proposed model is transformation invariant, which offers the necessary flexibility for real-time implementation in automated manufacturing systems. In addition, the numerical results for a set of ten reference shapes indicate that the matching engine can achieve very high success rates using short recognition times.

AB - Shape representation and recognition is an important topic in many applications of computer vision and artificial intelligence, including character recognition, pattern recognition, machine monitoring, robot manipulation and production part recognition. In this paper, a structural model based on boundary information is proposed to describe the silhouette of planar objects (especially machined parts). The structural model describes objects by a set of primitives, each of which is represented by three geometric features: its length, curvature, and relative orientation. This representation scheme not only compresses the data, but also provides a compact and meaningful form to facilitate further recognition operations. Based on this model, the object recognition is accomplished by using a multilayered feedforward neural network. The proposed model is transformation invariant, which offers the necessary flexibility for real-time implementation in automated manufacturing systems. In addition, the numerical results for a set of ten reference shapes indicate that the matching engine can achieve very high success rates using short recognition times.

UR - http://www.scopus.com/inward/record.url?scp=0030082592&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030082592&partnerID=8YFLogxK

U2 - 10.1007/BF00114134

DO - 10.1007/BF00114134

M3 - Article

AN - SCOPUS:0030082592

VL - 7

SP - 1

EP - 11

JO - Journal of Intelligent Manufacturing

JF - Journal of Intelligent Manufacturing

SN - 0956-5515

IS - 1

ER -