BibSonomy :: bibtex  ::

tag user group author concept BibTeX key search:all search:marcoalvarez
A blue social bookmark and publication sharing system.
tags · relations · groups · popular
help · blog · about
login · register
marcoalvarez's BibTeX entry:  

A comparison of pixel, edge and wavelet features for face detection using a semi-naive bayesian classifier

International Conference on Pattern Recognition, : 1175--1178, 2006.
Authors: J. Ross Beveridge and Jilmil Saraf and Ben Randall
URL: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1699735
Tags: Bayes ObjectDetection
Abstract: Henry Schneiderman at Carnegie Mellon University developed a face detection algorithm based upon a semi-naive Bayesian classifier and 5/3 linear phase wavelets. This paper explores the relative value of these wavelet features compared to simpler pixel and edge features. Experiments suggest edge features are superior for highly controlled lighting, while pixel features are better and more stable for uncontrolled lighting. Tests use the Notre Dame face data collected in Fall 2003 and Spring 2004 and use over 400,000 face and non-face test image chips.
| URL | BibTeX  
@inproceedings{Beveridge2006,
title = {A comparison of pixel, edge and wavelet features for face detection using a semi-naive bayesian classifier},
author = {J. Ross Beveridge and Jilmil Saraf and Ben Randall},
booktitle = {International Conference on Pattern Recognition},
pages = {1175--1178},
url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1699735},
year = {2006},
abstract = {Henry Schneiderman at Carnegie Mellon University developed a face detection algorithm based upon a semi-naive Bayesian classifier and 5/3 linear phase wavelets. This paper explores the relative value of these wavelet features compared to simpler pixel and edge features. Experiments suggest edge features are superior for highly controlled lighting, while pixel features are better and more stable for uncontrolled lighting. Tests use the Notre Dame face data collected in Fall 2003 and Spring 2004 and use over 400,000 face and non-face test image chips.},
keywords = {Bayes ObjectDetection }
}