Object recognition by affine invariant matching.

Yehezkel Lamdan*, Jacob T. Schwartz, Haim J. Wolfson

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

195 Scopus citations

Abstract

Novel techniques are described for model-based recognition of 3-D objects from unknown viewpoints using single-gray-scale images. The objects in the scene may be overlapping and partially occluded. Efficient matching algorithms, which assume affine approximation to the perspective viewing transformation, are proposed. The study is currently restricted to flat rigid 3-D objects. Point, line and curve matching algorithms are presented. The study especially emphasizes the curve matching problem. Experimental results are included.

Original languageEnglish
Title of host publicationProc CVPR 88 Comput Soc Conf on Comput Vision and Pattern Recognit
PublisherPubl by IEEE
Pages335-344
Number of pages10
ISBN (Print)0818608625
StatePublished - 1988
Externally publishedYes

Publication series

NameProc CVPR 88 Comput Soc Conf on Comput Vision and Pattern Recognit

Fingerprint

Dive into the research topics of 'Object recognition by affine invariant matching.'. Together they form a unique fingerprint.

Cite this