deposit_your_work

Machine recognition of occluded two-dimensional objects in clutter

Files in this item

Files Size Format View
1345315.PDF 4.401Mb application/pdf Thumbnail

Show full item record

Item Metadata

Title: Machine recognition of occluded two-dimensional objects in clutter
Author: Giritlioglu, Bogac
Advisor: de Figueiredo, Rui J. P.
Degree: Master of Science thesis
Abstract: This thesis presents a tree search based approach for recognizing occluded 2-D objects in clutter. The planar shapes are represented in terms of their contour line segments. Each is allowed three degrees of freedom (x, y translation and rotation) and a variable scaling factor. It is shown that incorrect pairings of line segments may be eliminated efficiently by using ordering of line segments, local, and global constraints. It is also shown by simulation and by mathematical bounds that the number of hypotheses consistent with these constraints is small.
Citation: Giritlioglu, Bogac. (1991) "Machine recognition of occluded two-dimensional objects in clutter." Masters Thesis, Rice University. http://hdl.handle.net/1911/13525.
URI: http://hdl.handle.net/1911/13525
Date: 1991

This item appears in the following Collection(s)