Data-driven indexed hypotheses for distorted shape matching

Author

Deb, Suash ; Majumder, D. Dutta

Author_Institution

Nat. Centre for Knowledge-Bases Comput., Indian Stat. Inst., Calcutta, India

fYear

1994

fDate

18-20 Jul 1994

Firstpage

378

Lastpage

383

Abstract

The problem of identification of multiple flat objects in a cluttered environment is dealt with. The objects become distorted due to occlusion, noise and other spurious effects. Unlike the previous model-based approaches involving exhaustive searching, this paper utilizes a data-driven indexing mechanism for model retrieval. Groups of consecutive segments, called super segments, are used as boundary descriptors. The whole approach is based on attributed string matching. With this technique model library can be modified as per requirement

Keywords

image matching; image segmentation; object recognition; robot vision; string matching; attributed string matching; boundary descriptors; cluttered environment; data-driven indexed hypotheses; distorted shape matching; image segmentation; model library; model retrieval; object recognition; occlusion; robot vision; super segments; Biosensors; Humans; Image segmentation; Intelligent robots; Intelligent sensors; Machine vision; Robot sensing systems; Robot vision systems; Shape; Uncertainty;

fLanguage

English

Publisher

ieee

Conference_Titel

Robot and Human Communication, 1994. RO-MAN '94 Nagoya, Proceedings., 3rd IEEE International Workshop on

Conference_Location

Nagoya

Print_ISBN

0-7803-2002-6

Type

conf

DOI

10.1109/ROMAN.1994.365899

Filename

365899