Show simple item record

dc.contributor.advisorZeigler, Bernard P.en_US
dc.contributor.authorHussain, Sheikh Akmal, 1963-
dc.creatorHussain, Sheikh Akmal, 1963-en_US
dc.date.accessioned2013-05-16T09:31:41Z
dc.date.available2013-05-16T09:31:41Z
dc.date.issued1991en_US
dc.identifier.urihttp://hdl.handle.net/10150/291586
dc.description.abstractObject identification is very important for Robotic Manipulation of objects. A study on potential has been done. Three prime techniques of features extraction have been analyzed: Vision, Touch and Destruction of materials (NDE). The role of perceptual organization in aiding object identification is also discussed. A list of features has been obtained for each technique. Evaluation, based on cost of computation and accuracy of computation, of techniques for features extraction is presented. Some sample object identification systems have been designed using Classification Expert System Maker (CESM). Use of D-matrix (distiguishability matrix) is emphasized to get the optimal feature set used to generate a classification tree. The classification tree is transferred into CESM knowledge base to obtain an expert system. A comprehensive multisensor system for object identification is proposed.
dc.language.isoen_USen_US
dc.publisherThe University of Arizona.en_US
dc.rightsCopyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.en_US
dc.subjectEngineering, Electronics and Electrical.en_US
dc.subjectEngineering, System Science.en_US
dc.subjectComputer Science.en_US
dc.titlePotential features for object identification by robotsen_US
dc.typetexten_US
dc.typeThesis-Reproduction (electronic)en_US
thesis.degree.grantorUniversity of Arizonaen_US
thesis.degree.levelmastersen_US
dc.identifier.proquest1346719en_US
thesis.degree.disciplineGraduate Collegeen_US
thesis.degree.disciplineElectrical and Computer Engineeringen_US
thesis.degree.nameM.S.en_US
dc.identifier.bibrecord.b27252796en_US
refterms.dateFOA2018-08-30T00:58:03Z
html.description.abstractObject identification is very important for Robotic Manipulation of objects. A study on potential has been done. Three prime techniques of features extraction have been analyzed: Vision, Touch and Destruction of materials (NDE). The role of perceptual organization in aiding object identification is also discussed. A list of features has been obtained for each technique. Evaluation, based on cost of computation and accuracy of computation, of techniques for features extraction is presented. Some sample object identification systems have been designed using Classification Expert System Maker (CESM). Use of D-matrix (distiguishability matrix) is emphasized to get the optimal feature set used to generate a classification tree. The classification tree is transferred into CESM knowledge base to obtain an expert system. A comprehensive multisensor system for object identification is proposed.


Files in this item

Thumbnail
Name:
azu_td_1346719_sip1_m.pdf
Size:
3.452Mb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record