|
With the rapid increase of computational powers and availability of modern sensing, analysis
and rendering equipment and technologies, computers are becoming more and more intelligent.
Many research projects and commercial products have demonstrated the capability for a computer
to interact with human in a natural way by looking at people through cameras, listening to people
through microphones, understanding these inputs, and reacting to people in a friendly manner.
One of the fundamental techniques that enables such natural human-computer interaction
(HCI) is face detection. Face detection is the step stone to all facial analysis algorithms, including
face alignment, face modeling, face relighting, face recognition, face verification/authentication, head
pose tracking, facial expression tracking/recognition, gender/age recognition, and many many more.
Only when computers can understand face well will they begin to truly understand people’s thoughts
and intentions.
It is a non-trivial task for a computer to detect faces in images or videos, and it has been one
of the most studied topics in the computer vision literature. It was not until the seminal work by
Viola and Jones (2001) that face detection became widely used in real world applications. Today, if
you buy a digital camera, most likely, it comes with face detection software to help auto-focusing
and auto-exposure. These face detectors works reasonably well, though challenges still remain due
to the huge variations of face images in scale, location, lighting, head pose, etc.
The authors of this book have worked intensely on the face detection problem in the past
4-5 years to further improve the original Viola-Jones detector (Viola and Jones, 2001). This book
is based on a number of our publications such as (Viola et al., 2005), (Zhang and Viola, 2007),
(Zhang et al., 2008a), (Zhang et al., 2008b), (Zhang and Zhang, 2009), (Wang et al., 2009b), etc. It
is our hope that by sharing some of the lessons we learned during our exploration, we will see even
better algorithms developed to solve this fundamental computer vision problem.
We would like to take this opportunity to give our special thanks to Paul Viola, one of the
designers of the original boosting-based face detector, with whom we developed some of the key
algorithms presented in this book.We would also like to thank other co-authors of those papers,
namely, John Platt, Raffay Hamid, Pei Yin, Yong Rui, Ross Cutler, Xinding Sun, Nelson Pinto,
and Xiaogang Wang.We would also like to thank Rong Xiao, with whom we had many valuable
discussions while developing some of the algorithms presented in this book. |