<html>
<head>
<meta http-equiv="content-type" content="text/html;
charset=ISO-8859-1">
</head>
<body bgcolor="#FFFFFF" text="#000000">
A new article is available in IPOL:
<a class="moz-txt-link-freetext" href="http://www.ipol.im/pub/art/2014/104/">http://www.ipol.im/pub/art/2014/104/</a><br>
<br>
<meta charset="utf-8">
Yi-Qing Wang, <br>
An Analysis of the Viola-Jones Face Detection Algorithm, <br>
Image Processing On Line, 4 (2014), pp. 128–148. <br>
<a class="moz-txt-link-freetext" href="http://dx.doi.org/10.5201/ipol.2014.104">http://dx.doi.org/10.5201/ipol.2014.104</a><br>
<br>
Abstract<br>
In this article, we decipher the Viola-Jones algorithm, the first
ever real-time face detection system. There are three ingredients
working in concert to enable a fast and accurate detection: the
integral image for feature computation, Adaboost for feature
selection and an attentional cascade for efficient computational
resource allocation. Here we propose a complete algorithmic
description, a learning code and a learned face detector that can be
applied to any color image. Since the Viola-Jones algorithm
typically gives multiple detections, a post-processing step is also
proposed to reduce detection redundancy using a robustness argument.<br>
<br>
<br>
<br>
</body>
</html>