Object localization using deformable templates

DSpace/Manakin Repository

Show simple item record

dc.contributor.author Spiller, Jonathan Michael
dc.date.accessioned 2008-03-12T11:01:48Z
dc.date.available 2008-03-12T11:01:48Z
dc.date.issued 2008-03-12T11:01:48Z
dc.identifier.uri http://hdl.handle.net/10539/4662
dc.description.abstract Object localization refers to the detection, matching and segmentation of objects in images. The localization model presented in this paper relies on deformable templates to match objects based on shape alone. The shape structure is captured by a prototype template consisting of hand-drawn edges and contours representing the object to be localized. A multistage, multiresolution algorithm is utilized to reduce the computational intensity of the search. The first stage reduces the physical search space dimensions using correlation to determine the regions of interest where a match it likely to occur. The second stage finds approximate matches between the template and target image at progressively finer resolutions, by attracting the template to salient image features using Edge Potential Fields. The third stage entails the use of evolutionary optimization to determine control point placement for a Local Weighted Mean warp, which deforms the template to fit the object boundaries. Results are presented for a number of applications, showing the successful localization of various objects. The algorithm’s invariance to rotation, scale, translation and moderate shape variation of the target objects is clearly illustrated. en
dc.format.extent 3332677 bytes
dc.format.mimetype application/pdf
dc.language.iso en en
dc.subject deformable template en
dc.subject localization en
dc.subject multiresolution algorithm en
dc.title Object localization using deformable templates en
dc.type Thesis en


Files in this item

This item appears in the following Collection(s)

  • ETD Collection
    Thesis (Ph.D.)--University of the Witwatersrand, 1972.

Show simple item record

Search WIReDSpace


Browse

My Account

Statistics