Object Recognition with Pictorial Structures
This thesis presents a statistical framework for object recognition. The framework is motivated by the pictorial structure models introduced by Fischler and Elschlager nearly 30 years ago. The basic idea is to model an object by a collection of parts arranged in a deformable configuration. The appea...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/7073 |
| _version_ | 1826207101443112960 |
|---|---|
| author | Felzenszwalb, Pedro F. |
| author_facet | Felzenszwalb, Pedro F. |
| author_sort | Felzenszwalb, Pedro F. |
| collection | MIT |
| description | This thesis presents a statistical framework for object recognition. The framework is motivated by the pictorial structure models introduced by Fischler and Elschlager nearly 30 years ago. The basic idea is to model an object by a collection of parts arranged in a deformable configuration. The appearance of each part is modeled separately, and the deformable configuration is represented by spring-like connections between pairs of parts. These models allow for qualitative descriptions of visual appearance, and are suitable for generic recognition problems. The problem of detecting an object in an image and the problem of learning an object model using training examples are naturally formulated under a statistical approach. We present efficient algorithms to solve these problems in our framework. We demonstrate our techniques by training models to represent faces and human bodies. The models are then used to locate the corresponding objects in novel images. |
| first_indexed | 2024-09-23T13:44:08Z |
| id | mit-1721.1/7073 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T13:44:08Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/70732019-04-12T08:33:53Z Object Recognition with Pictorial Structures Felzenszwalb, Pedro F. This thesis presents a statistical framework for object recognition. The framework is motivated by the pictorial structure models introduced by Fischler and Elschlager nearly 30 years ago. The basic idea is to model an object by a collection of parts arranged in a deformable configuration. The appearance of each part is modeled separately, and the deformable configuration is represented by spring-like connections between pairs of parts. These models allow for qualitative descriptions of visual appearance, and are suitable for generic recognition problems. The problem of detecting an object in an image and the problem of learning an object model using training examples are naturally formulated under a statistical approach. We present efficient algorithms to solve these problems in our framework. We demonstrate our techniques by training models to represent faces and human bodies. The models are then used to locate the corresponding objects in novel images. 2004-10-20T20:28:15Z 2004-10-20T20:28:15Z 2001-05-01 AITR-2001-002 http://hdl.handle.net/1721.1/7073 en_US AITR-2001-002 15588217 bytes 1282972 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Felzenszwalb, Pedro F. Object Recognition with Pictorial Structures |
| title | Object Recognition with Pictorial Structures |
| title_full | Object Recognition with Pictorial Structures |
| title_fullStr | Object Recognition with Pictorial Structures |
| title_full_unstemmed | Object Recognition with Pictorial Structures |
| title_short | Object Recognition with Pictorial Structures |
| title_sort | object recognition with pictorial structures |
| url | http://hdl.handle.net/1721.1/7073 |
| work_keys_str_mv | AT felzenszwalbpedrof objectrecognitionwithpictorialstructures |