New algorithm for partial shape matching

Meng Chien Yang, Kishan Mehrotra, Chilukuri K. Mohan, Sanjay Ranka

Research output: Contribution to conferencePaper

3 Scopus citations

Abstract

We modify and combine the attribute grammar shape matching algorithm with a two-layer neural network. The first layer of the network matches input images with a model, and the second layer verifies the results thereof. Experimental results show that this network can simulate symbolic shape matching, and successfully performs the partial matching. A parallel implementation of the algorithm has been built and tested.

Original languageEnglish (US)
Pages523-528
Number of pages6
StatePublished - Dec 1 1992
EventProceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92 - St.Louis, MO, USA
Duration: Nov 15 1992Nov 18 1992

Other

OtherProceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92
CitySt.Louis, MO, USA
Period11/15/9211/18/92

ASJC Scopus subject areas

  • Software

Fingerprint Dive into the research topics of 'New algorithm for partial shape matching'. Together they form a unique fingerprint.

  • Cite this

    Yang, M. C., Mehrotra, K., Mohan, C. K., & Ranka, S. (1992). New algorithm for partial shape matching. 523-528. Paper presented at Proceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92, St.Louis, MO, USA, .