| dc.contributor.author |
Felzenszwalb, Pedro F. |
|
| dc.date.accessioned |
2005-12-19T22:44:55Z |
|
| dc.date.available |
2005-12-19T22:44:55Z |
|
| dc.date.issued |
2003-08-08 |
|
| dc.identifier.other |
MIT-CSAIL-TR-2003-008 |
|
| dc.identifier.other |
AITR-2003-016 |
|
| dc.identifier.uri |
http://hdl.handle.net/1721.1/30400 |
|
| dc.description.abstract |
We present a set of techniques that can be used to represent anddetect shapes in images. Our methods revolve around a particularshape representation based on the description of objects usingtriangulated polygons. This representation is similar to the medialaxis transform and has important properties from a computationalperspective. The first problem we consider is the detection ofnon-rigid objects in images using deformable models. We present anefficient algorithm to solve this problem in a wide range ofsituations, and show examples in both natural and medical images. Wealso consider the problem of learning an accurate non-rigid shapemodel for a class of objects from examples. We show how to learn goodmodels while constraining them to the form required by the detectionalgorithm. Finally, we consider the problem of low-level imagesegmentation and grouping. We describe a stochastic grammar thatgenerates arbitrary triangulated polygons while capturing Gestaltprinciples of shape regularity. This grammar is used as a prior modelover random shapes in a low level algorithm that detects objects inimages. |
|
| dc.description.provenance |
Made available in DSpace on 2005-12-19T22:44:55Z (GMT). No. of bitstreams: 2
MIT-CSAIL-TR-2003-008.ps: 38103057 bytes, checksum: cf300bd9251a32f4d9ba4c91eb05495f (MD5)
MIT-CSAIL-TR-2003-008.pdf: 1889641 bytes, checksum: 74cea628e90e521cb941157be4b6b99c (MD5) |
en |
| dc.format.extent |
80 p. |
|
| dc.format.extent |
38103057 bytes |
|
| dc.format.extent |
1889641 bytes |
|
| dc.format.mimetype |
application/postscript |
|
| dc.format.mimetype |
application/pdf |
|
| dc.language.iso |
en_US |
|
| dc.relation.ispartofseries |
Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory |
|
| dc.subject |
AI |
|
| dc.title |
Representation and Detection of Shapes in Images |
|
