Fast Object Recognition in Noisy Images Using Simulated Annealing
A fast simulated annealing algorithm is developed for automatic object recognition. The normalized correlation coefficient is used as a measure of the match between a hypothesized object and an image. Templates are generated on-line during the search by transforming model images. Simulated an...
| Main Authors: | , |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/7199 |
| _version_ | 1826215392390938624 |
|---|---|
| author | Betke, Margrit Makris, Nicholas |
| author_facet | Betke, Margrit Makris, Nicholas |
| author_sort | Betke, Margrit |
| collection | MIT |
| description | A fast simulated annealing algorithm is developed for automatic object recognition. The normalized correlation coefficient is used as a measure of the match between a hypothesized object and an image. Templates are generated on-line during the search by transforming model images. Simulated annealing reduces the search time by orders of magnitude with respect to an exhaustive search. The algorithm is applied to the problem of how landmarks, for example, traffic signs, can be recognized by an autonomous vehicle or a navigating robot. The algorithm works well in noisy, real-world images of complicated scenes for model images with high information content. |
| first_indexed | 2024-09-23T16:26:56Z |
| id | mit-1721.1/7199 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T16:26:56Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/71992019-04-10T11:52:44Z Fast Object Recognition in Noisy Images Using Simulated Annealing Betke, Margrit Makris, Nicholas Template matching ; Fast simulated annealing; Information content of images; Traffic sign recognition for mobile robots or autonomous vehicles A fast simulated annealing algorithm is developed for automatic object recognition. The normalized correlation coefficient is used as a measure of the match between a hypothesized object and an image. Templates are generated on-line during the search by transforming model images. Simulated annealing reduces the search time by orders of magnitude with respect to an exhaustive search. The algorithm is applied to the problem of how landmarks, for example, traffic signs, can be recognized by an autonomous vehicle or a navigating robot. The algorithm works well in noisy, real-world images of complicated scenes for model images with high information content. 2004-10-20T20:49:32Z 2004-10-20T20:49:32Z 1995-01-25 AIM-1510 CBCL-109 http://hdl.handle.net/1721.1/7199 en_US AIM-1510 CBCL-109 9 p. 1311904 bytes 735998 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Template matching ; Fast simulated annealing; Information content of images; Traffic sign recognition for mobile robots or autonomous vehicles Betke, Margrit Makris, Nicholas Fast Object Recognition in Noisy Images Using Simulated Annealing |
| title | Fast Object Recognition in Noisy Images Using Simulated Annealing |
| title_full | Fast Object Recognition in Noisy Images Using Simulated Annealing |
| title_fullStr | Fast Object Recognition in Noisy Images Using Simulated Annealing |
| title_full_unstemmed | Fast Object Recognition in Noisy Images Using Simulated Annealing |
| title_short | Fast Object Recognition in Noisy Images Using Simulated Annealing |
| title_sort | fast object recognition in noisy images using simulated annealing |
| topic | Template matching ; Fast simulated annealing; Information content of images; Traffic sign recognition for mobile robots or autonomous vehicles |
| url | http://hdl.handle.net/1721.1/7199 |
| work_keys_str_mv | AT betkemargrit fastobjectrecognitioninnoisyimagesusingsimulatedannealing AT makrisnicholas fastobjectrecognitioninnoisyimagesusingsimulatedannealing |