Edge orientation-based multi-view object recognition

Research output: Contribution to journalArticlepeer-review

Abstract

An edge orientation-based algorithm for multi-view object recognition is presented in this paper. The distribution of edge point orientations, combined with the normalized second moments, is taken as a feature vector to describe and index each object instance. For each unknown testing object, a set of likelihood weights for all the possible candidate objects is obtained by computing the Euclidean distances between the unknown feature set and all the available template feature vectors. A convincing coefficient is introduced to evaluate the confidence of the best match. New views (photo shots) will be automatically taken if the best match is thought to be insufficiently convincing. In the experiments, our algorithm has achieved an average of 97.5% correct recognition rate under the 5-view scheme for 320 testing images taken from eight natural objects.

Original languageEnglish (US)
Pages (from-to)936-939
Number of pages4
JournalProceedings - International Conference on Pattern Recognition
Volume15
Issue number1
StatePublished - Dec 1 2000

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Edge orientation-based multi-view object recognition'. Together they form a unique fingerprint.

Cite this