Complex Feature Recognition: A Bayesian Approach for Learning to Recognize Objects
We have developed a new Bayesian framework for visual object recognition which is based on the insight that images of objects can be modeled as a conjunction of local features. This framework can be used to both derive an object recognition algorithm and an algorithm for learning the features...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/5940 |
| _version_ | 1826216375753900032 |
|---|---|
| author | Viola, Paul |
| author_facet | Viola, Paul |
| author_sort | Viola, Paul |
| collection | MIT |
| description | We have developed a new Bayesian framework for visual object recognition which is based on the insight that images of objects can be modeled as a conjunction of local features. This framework can be used to both derive an object recognition algorithm and an algorithm for learning the features themselves. The overall approach, called complex feature recognition or CFR, is unique for several reasons: it is broadly applicable to a wide range of object types, it makes constructing object models easy, it is capable of identifying either the class or the identity of an object, and it is computationally efficient--requiring time proportional to the size of the image. Instead of a single simple feature such as an edge, CFR uses a large set of complex features that are learned from experience with model objects. The response of a single complex feature contains much more class information than does a single edge. This significantly reduces the number of possible correspondences between the model and the image. In addition, CFR takes advantage of a type of image processing called 'oriented energy'. Oriented energy is used to efficiently pre-process the image to eliminate some of the difficulties associated with changes in lighting and pose. |
| first_indexed | 2024-09-23T16:46:40Z |
| id | mit-1721.1/5940 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T16:46:40Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/59402019-04-12T08:28:14Z Complex Feature Recognition: A Bayesian Approach for Learning to Recognize Objects Viola, Paul AI MIT Artificial Intelligence statistical inference bayesian vision recognition We have developed a new Bayesian framework for visual object recognition which is based on the insight that images of objects can be modeled as a conjunction of local features. This framework can be used to both derive an object recognition algorithm and an algorithm for learning the features themselves. The overall approach, called complex feature recognition or CFR, is unique for several reasons: it is broadly applicable to a wide range of object types, it makes constructing object models easy, it is capable of identifying either the class or the identity of an object, and it is computationally efficient--requiring time proportional to the size of the image. Instead of a single simple feature such as an edge, CFR uses a large set of complex features that are learned from experience with model objects. The response of a single complex feature contains much more class information than does a single edge. This significantly reduces the number of possible correspondences between the model and the image. In addition, CFR takes advantage of a type of image processing called 'oriented energy'. Oriented energy is used to efficiently pre-process the image to eliminate some of the difficulties associated with changes in lighting and pose. 2004-10-04T14:15:44Z 2004-10-04T14:15:44Z 1996-11-01 AIM-1591 http://hdl.handle.net/1721.1/5940 en_US AIM-1591 29 p. 1626255 bytes 694971 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | AI MIT Artificial Intelligence statistical inference bayesian vision recognition Viola, Paul Complex Feature Recognition: A Bayesian Approach for Learning to Recognize Objects |
| title | Complex Feature Recognition: A Bayesian Approach for Learning to Recognize Objects |
| title_full | Complex Feature Recognition: A Bayesian Approach for Learning to Recognize Objects |
| title_fullStr | Complex Feature Recognition: A Bayesian Approach for Learning to Recognize Objects |
| title_full_unstemmed | Complex Feature Recognition: A Bayesian Approach for Learning to Recognize Objects |
| title_short | Complex Feature Recognition: A Bayesian Approach for Learning to Recognize Objects |
| title_sort | complex feature recognition a bayesian approach for learning to recognize objects |
| topic | AI MIT Artificial Intelligence statistical inference bayesian vision recognition |
| url | http://hdl.handle.net/1721.1/5940 |
| work_keys_str_mv | AT violapaul complexfeaturerecognitionabayesianapproachforlearningtorecognizeobjects |