Face Detection with Asymmetric Boosting

ISBN-13: 9783639178326 / Angielski / Miękka / 2009 / 120 str.

Minh-Tri Pham

Opis

Asymmetric boosting, while acknowledged to beimportant to state-of-the-art face detection, istypically based on the trial-and-error practice,rather than on principled methods. This work solves anumber of issues related to asymmetric boosting andthe use of asymmetric boosting in face detection. Itshows how a proper understanding and use ofasymmetric boosting leads to significant improvementsin thelearning time, the learning capacity, the detectionspeed and the detection accuracy of a face detector.There are four main contributions in this book: 1) anew method to learn online an asymmetric boostedclassifier, pioneering a new direction of onlinelearning a face detector; 2) a new weak classifierlearning method,significantly reducing the learning time of aface detector from weeks to just a few hours; 3) anew and principled method to learn aface detector cascade, further improvingthe learning time and the detection speed of a facedetector; and 4) a theoretical analysis on thegeneralization of an asymmetric boosted classifiervia bounds on the trueasymmetric error of the classifier. The work isconcluded with a discussion of future directions forface detection.

O autorze

Minh-Tri Pham is a Research Fellow in computer science at the
School of Computer Engineering, Nanyang Technological University,
Singapore. Tat-Jen Cham is an Associate Professor in computer
science and the Director of the Centre for Multimedia and Network
Technology, School of Computer Engineering, Nanyang Technological
University, Singapore.