Component based recognition of objects in an office environment
We present a component-based approach for recognizing objectsunder large pose changes. From a set of training images of a givenobject we extract a large number of components which are clusteredbased on the similarity of their image features and their locations withinthe object image. The cluster cen...
| Main Authors: | , |
|---|---|
| Language: | en_US |
| Published: |
2005
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/30436 |
| _version_ | 1826207712149504000 |
|---|---|
| author | Morgenstern, Christian Heisele, Bernd |
| author_facet | Morgenstern, Christian Heisele, Bernd |
| author_sort | Morgenstern, Christian |
| collection | MIT |
| description | We present a component-based approach for recognizing objectsunder large pose changes. From a set of training images of a givenobject we extract a large number of components which are clusteredbased on the similarity of their image features and their locations withinthe object image. The cluster centers build an initial set of componenttemplates from which we select a subset for the final recognizer.In experiments we evaluate different sizes and types of components andthree standard techniques for component selection. The component classifiersare finally compared to global classifiers on a database of fourobjects. |
| first_indexed | 2024-09-23T13:53:47Z |
| id | mit-1721.1/30436 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T13:53:47Z |
| publishDate | 2005 |
| record_format | dspace |
| spelling | mit-1721.1/304362019-04-11T04:57:52Z Component based recognition of objects in an office environment Morgenstern, Christian Heisele, Bernd AI computer vision object recognition component object recognition We present a component-based approach for recognizing objectsunder large pose changes. From a set of training images of a givenobject we extract a large number of components which are clusteredbased on the similarity of their image features and their locations withinthe object image. The cluster centers build an initial set of componenttemplates from which we select a subset for the final recognizer.In experiments we evaluate different sizes and types of components andthree standard techniques for component selection. The component classifiersare finally compared to global classifiers on a database of fourobjects. 2005-12-22T01:15:11Z 2005-12-22T01:15:11Z 2003-11-28 MIT-CSAIL-TR-2003-031 AIM-2003-024 CBCL-232 http://hdl.handle.net/1721.1/30436 en_US Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory 12 p. 20676042 bytes 965767 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | AI computer vision object recognition component object recognition Morgenstern, Christian Heisele, Bernd Component based recognition of objects in an office environment |
| title | Component based recognition of objects in an office environment |
| title_full | Component based recognition of objects in an office environment |
| title_fullStr | Component based recognition of objects in an office environment |
| title_full_unstemmed | Component based recognition of objects in an office environment |
| title_short | Component based recognition of objects in an office environment |
| title_sort | component based recognition of objects in an office environment |
| topic | AI computer vision object recognition component object recognition |
| url | http://hdl.handle.net/1721.1/30436 |
| work_keys_str_mv | AT morgensternchristian componentbasedrecognitionofobjectsinanofficeenvironment AT heiselebernd componentbasedrecognitionofobjectsinanofficeenvironment |