People Recognition in Image Sequences by Supervised Learning
We describe a system that learns from examples to recognize people in images taken indoors. Images of people are represented by color-based and shape-based features. Recognition is carried out through combinations of Support Vector Machine classifiers (SVMs). Different types of multiclass strategies...
| Main Authors: | , , , |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/7230 |
| _version_ | 1811081403785281536 |
|---|---|
| author | Nakajima, Chikahito Pontil, Massimiliano Heisele, Bernd Poggio, Tomaso |
| author_facet | Nakajima, Chikahito Pontil, Massimiliano Heisele, Bernd Poggio, Tomaso |
| author_sort | Nakajima, Chikahito |
| collection | MIT |
| description | We describe a system that learns from examples to recognize people in images taken indoors. Images of people are represented by color-based and shape-based features. Recognition is carried out through combinations of Support Vector Machine classifiers (SVMs). Different types of multiclass strategies based on SVMs are explored and compared to k-Nearest Neighbors classifiers (kNNs). The system works in real time and shows high performance rates for people recognition throughout one day. |
| first_indexed | 2024-09-23T11:45:50Z |
| id | mit-1721.1/7230 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T11:45:50Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/72302019-04-12T08:34:08Z People Recognition in Image Sequences by Supervised Learning Nakajima, Chikahito Pontil, Massimiliano Heisele, Bernd Poggio, Tomaso We describe a system that learns from examples to recognize people in images taken indoors. Images of people are represented by color-based and shape-based features. Recognition is carried out through combinations of Support Vector Machine classifiers (SVMs). Different types of multiclass strategies based on SVMs are explored and compared to k-Nearest Neighbors classifiers (kNNs). The system works in real time and shows high performance rates for people recognition throughout one day. 2004-10-20T21:03:31Z 2004-10-20T21:03:31Z 2000-06-01 AIM-1688 CBCL-188 http://hdl.handle.net/1721.1/7230 en_US AIM-1688 CBCL-188 4611797 bytes 373760 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Nakajima, Chikahito Pontil, Massimiliano Heisele, Bernd Poggio, Tomaso People Recognition in Image Sequences by Supervised Learning |
| title | People Recognition in Image Sequences by Supervised Learning |
| title_full | People Recognition in Image Sequences by Supervised Learning |
| title_fullStr | People Recognition in Image Sequences by Supervised Learning |
| title_full_unstemmed | People Recognition in Image Sequences by Supervised Learning |
| title_short | People Recognition in Image Sequences by Supervised Learning |
| title_sort | people recognition in image sequences by supervised learning |
| url | http://hdl.handle.net/1721.1/7230 |
| work_keys_str_mv | AT nakajimachikahito peoplerecognitioninimagesequencesbysupervisedlearning AT pontilmassimiliano peoplerecognitioninimagesequencesbysupervisedlearning AT heiselebernd peoplerecognitioninimagesequencesbysupervisedlearning AT poggiotomaso peoplerecognitioninimagesequencesbysupervisedlearning |