File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: TWO-DIMENSIONAL OBJECT RECOGNITION USING MULTIRESOLUTION MODELS.

TitleTWO-DIMENSIONAL OBJECT RECOGNITION USING MULTIRESOLUTION MODELS.
Authors
KeywordsCOMPUTER PROGRAMMING - Algorithms
IMAGE PROCESSING
Issue Date1986
Citation
Computer Vision, Graphics, And Image Processing, 1986, v. 34 n. 1, p. 52-65 How to Cite?
AbstractA multiresolution, model-based matching technique is described for coarse-to-fine object recognition. Each two-dimensional object is modeled as a directed acyclic graph. Each node in the graph stores a boundary segment of the object model at a selected level of spatial resolution. The root node of the graph contains the coarsest resolution representation of the boundary of the object, leaf nodes contain sections of the boundary at the highest resolution, and intermediate nodes contain features at intermediate levels of resolution. Arcs are directed from boundary segments at one level of resolution to spatially related boundary segments at finer levels of resolution. A generalized Hough transform is used to match the model nodes with regions in the corresponding level of resolution in a given input image pyramid.
Persistent Identifierhttp://hdl.handle.net/10722/65511
ISSN

 

DC FieldValueLanguage
dc.contributor.authorNeveu, Charles Fen_HK
dc.contributor.authorDyer, Charles Ren_HK
dc.contributor.authorChin, Roland Ten_HK
dc.date.accessioned2010-08-31T07:14:54Z-
dc.date.available2010-08-31T07:14:54Z-
dc.date.issued1986en_HK
dc.identifier.citationComputer Vision, Graphics, And Image Processing, 1986, v. 34 n. 1, p. 52-65en_HK
dc.identifier.issn0734-189Xen_HK
dc.identifier.urihttp://hdl.handle.net/10722/65511-
dc.description.abstractA multiresolution, model-based matching technique is described for coarse-to-fine object recognition. Each two-dimensional object is modeled as a directed acyclic graph. Each node in the graph stores a boundary segment of the object model at a selected level of spatial resolution. The root node of the graph contains the coarsest resolution representation of the boundary of the object, leaf nodes contain sections of the boundary at the highest resolution, and intermediate nodes contain features at intermediate levels of resolution. Arcs are directed from boundary segments at one level of resolution to spatially related boundary segments at finer levels of resolution. A generalized Hough transform is used to match the model nodes with regions in the corresponding level of resolution in a given input image pyramid.en_HK
dc.languageengen_HK
dc.relation.ispartofComputer vision, graphics, and image processingen_HK
dc.subjectCOMPUTER PROGRAMMING - Algorithmsen_HK
dc.subjectIMAGE PROCESSINGen_HK
dc.titleTWO-DIMENSIONAL OBJECT RECOGNITION USING MULTIRESOLUTION MODELS.en_HK
dc.typeArticleen_HK
dc.identifier.emailChin, Roland T: rchin@hku.hken_HK
dc.identifier.authorityChin, Roland T=rp01300en_HK
dc.description.naturelink_to_subscribed_fulltexten_HK
dc.identifier.scopuseid_2-s2.0-0022696358en_HK
dc.identifier.volume34en_HK
dc.identifier.issue1en_HK
dc.identifier.spage52en_HK
dc.identifier.epage65en_HK
dc.identifier.scopusauthoridNeveu, Charles F=55411109500en_HK
dc.identifier.scopusauthoridDyer, Charles R=7202510459en_HK
dc.identifier.scopusauthoridChin, Roland T=7102445426en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats