Example Based Learning for View-Based Human Face Detection

We present an example-based learning approach for locating vertical frontal views of human faces in complex scenes. The technique models the distribution of human face patterns by means of a few view-based "face'' and "non-face'' prototype clusters. At each image...

Full description

Bibliographic Details
Main Authors: Sung, Kah Kay, Poggio, Tomaso
Language:en_US
Published: 2004
Subjects:
Online Access:http://hdl.handle.net/1721.1/7193
_version_ 1826205270072623104
author Sung, Kah Kay
Poggio, Tomaso
author_facet Sung, Kah Kay
Poggio, Tomaso
author_sort Sung, Kah Kay
collection MIT
description We present an example-based learning approach for locating vertical frontal views of human faces in complex scenes. The technique models the distribution of human face patterns by means of a few view-based "face'' and "non-face'' prototype clusters. At each image location, the local pattern is matched against the distribution-based model, and a trained classifier determines, based on the local difference measurements, whether or not a human face exists at the current image location. We provide an analysis that helps identify the critical components of our system.
first_indexed 2024-09-23T13:10:01Z
id mit-1721.1/7193
institution Massachusetts Institute of Technology
language en_US
last_indexed 2024-09-23T13:10:01Z
publishDate 2004
record_format dspace
spelling mit-1721.1/71932019-04-10T11:52:41Z Example Based Learning for View-Based Human Face Detection Sung, Kah Kay Poggio, Tomaso Face Detection Pattern Recognition Pattern Classification Learning from examples Object Recognition We present an example-based learning approach for locating vertical frontal views of human faces in complex scenes. The technique models the distribution of human face patterns by means of a few view-based "face'' and "non-face'' prototype clusters. At each image location, the local pattern is matched against the distribution-based model, and a trained classifier determines, based on the local difference measurements, whether or not a human face exists at the current image location. We provide an analysis that helps identify the critical components of our system. 2004-10-20T20:49:22Z 2004-10-20T20:49:22Z 1995-01-24 AIM-1521 CBCL-112 http://hdl.handle.net/1721.1/7193 en_US AIM-1521 CBCL-112 21 p. 2933946 bytes 846344 bytes application/postscript application/pdf application/postscript application/pdf
spellingShingle Face Detection Pattern Recognition Pattern Classification Learning from examples Object Recognition
Sung, Kah Kay
Poggio, Tomaso
Example Based Learning for View-Based Human Face Detection
title Example Based Learning for View-Based Human Face Detection
title_full Example Based Learning for View-Based Human Face Detection
title_fullStr Example Based Learning for View-Based Human Face Detection
title_full_unstemmed Example Based Learning for View-Based Human Face Detection
title_short Example Based Learning for View-Based Human Face Detection
title_sort example based learning for view based human face detection
topic Face Detection Pattern Recognition Pattern Classification Learning from examples Object Recognition
url http://hdl.handle.net/1721.1/7193
work_keys_str_mv AT sungkahkay examplebasedlearningforviewbasedhumanfacedetection
AT poggiotomaso examplebasedlearningforviewbasedhumanfacedetection