A vision system for automatic object recognition

QSpace/Manakin Repository

A vision system for automatic object recognition

Show simple item record


dc.contributor.author Bennamoun, M
dc.contributor.author Boashash, B
dc.date.accessioned 2012-03-20T18:25:24Z
dc.date.available 2012-03-20T18:25:24Z
dc.date.issued 1994-10
dc.identifier.citation Systems, Man, and Cybernetics, 1994. 'Humans, Information and Technology'., 1994 IEEE International Conference on Issue Date: 2-5 Oct 1994 On page(s): 1369 - 1374 vol. 2 en_US
dc.identifier.isbn 0-7803-2129-4
dc.identifier.uri http://hdl.handle.net/10576/10805
dc.description This paper presents a new multistage vision system for 2-D object recognition, composed of a modular structure which makes it open to continual improvement. en_US
dc.description.abstract This paper presents the results of the integration of a proposed vision system based on the decomposition of objects into parts. The objects are defined by their contours which are obtained using a hybrid first and second-order differential edge detector. The parts are isolated, and their parameters modelled by 2-D superquadrics, are obtained by the minimization of a best-fit cost function. The object is then represented by its structural description which are data structure whose predicates represent the parts and whose arguments represent the spatial relationship between the parts. This representation allows the recognition of objects independently of their position, orientation or size and is insensitive to partially missing parts. In this paper, examples illustrating acquired images of objects, the extraction of their contours, the isolation of the parts, and their fitting with 2-D superquadrics are reported. The recognition rate of the suggested vision system for simultaneously and randomly rotated, displaced and resized objects is also reported. This framework can also be used for the compression of images, where only an ASCII file describing the structural representation of the object is transmitted. The reconstruction of objects from their structural description is reported and improvements are suggested. en_US
dc.language.iso en en_US
dc.publisher IEEE en_US
dc.subject 2D superquadrics en_US
dc.subject ASCII file en_US
dc.subject automatic object recognition en_US
dc.subject best-fit cost function minimization en_US
dc.subject contour extraction en_US
dc.subject data structure en_US
dc.subject differential edge detector en_US
dc.subject image compression en_US
dc.subject object decomposition en_US
dc.subject object images en_US
dc.subject parameter estimation en_US
dc.subject parts isolation en_US
dc.subject spatial relationship en_US
dc.subject structural description en_US
dc.subject vision system integration en_US
dc.title A vision system for automatic object recognition en_US
dc.type Article en_US

Files in this item

Files Size Format View
Boashash-Bennam ... n_Cybern_vision-system.pdf 574.9Kb PDF View/Open

This item appears in the following Collection(s)

Show simple item record

Search QSpace


Advanced Search

Browse

My Account