Gabor-Boosting Face Recognition: From Machine Learning Perspective

Research output: Book/Report/Edited volumeBookpeer-review

Abstract

In the past decade, face recognition has received much attention by both the commercial and public sectors in biometrics. This book describes a highly accurate appearance-based approach for face recognition - Gabor-Boosting.The strong performance of the Gabor-Boosting face recognition is highlighted by combining three key leading edge techniques - Gabor wavelet transform, AdaBoost, Support Vector Machine (SVM). The Gabor wavelet transform is used to extract features which describe texture variations of human faces. The AdaBoost algorithm is used to select most significant features which represent different individuals. The SVM constructs a classifier with high recognition accuracy. The Gabor-Boosting face recognition is extended into multi-class classification domain. The results show that the performance is improved by applying loosely controlled face recognition in the multi-class classification. The Gabor-Boosting face recognition is robust under conditions of small number of examples and selection-bias. It gives no false detections for impostors and high acceptance rate for clients in face verification.
Original languageEnglish
Publisher VDM Verlag Dr. Müller
Number of pages256
ISBN (Electronic)978-3639214604
ISBN (Print)9783639214604
Publication statusPublished - 22 Nov 2009

Fingerprint

Dive into the research topics of 'Gabor-Boosting Face Recognition: From Machine Learning Perspective'. Together they form a unique fingerprint.

Cite this