Shape recognition for machined parts

Jose Antonio Ventura, Jen Ming Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, a structural model based on boundary information is proposed to describe the silhouette of planar objects (esp. machined parts). The structural model describes objects by a set of primitives, which compresses the data, saves the computer space, and provides a compact and meaningful form to facilitate further recognition operation. The object recognition is then accomplished by using a multi-layered feed-forward neural network. The proposed model is transformation invariant which offers the necessary flexibility for real time implementation.

Original languageEnglish (US)
Title of host publicationProceedings of the Industrial Engineering Research Conference
EditorsDeborah A. Mitta, Laura I. Burke, John R. English, Jennie Gallimore, Georgia-Ann Klutke, Gregory L. Tonkay
PublisherPubl by IIE
Pages694-699
Number of pages6
ISBN (Print)0898061326
StatePublished - Dec 1 1993
EventProceedings of the 2nd Industrial Engineering Research Conference - Los Angeles, CA, USA
Duration: May 26 1993May 28 1993

Publication series

NameProceedings of the Industrial Engineering Research Conference

Other

OtherProceedings of the 2nd Industrial Engineering Research Conference
CityLos Angeles, CA, USA
Period5/26/935/28/93

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Fingerprint Dive into the research topics of 'Shape recognition for machined parts'. Together they form a unique fingerprint.

  • Cite this

    Ventura, J. A., & Chen, J. M. (1993). Shape recognition for machined parts. In D. A. Mitta, L. I. Burke, J. R. English, J. Gallimore, G-A. Klutke, & G. L. Tonkay (Eds.), Proceedings of the Industrial Engineering Research Conference (pp. 694-699). (Proceedings of the Industrial Engineering Research Conference). Publ by IIE.