Glasses detection by boosting simple wavelet features

Author

Wu, Bo ; Ai, Haizhou ; Liu, Ran

Author_Institution

Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China

Volume

1

fYear

2004

fDate

23-26 Aug. 2004

Firstpage

292

Abstract

We propose a novel method for glasses detection. The glasses detectors are learned by using a variation of boosting algorithm, called real Adaboost, to boost simple wavelet feature based Look-Up-Table type weak classifiers. Two types of wavelet features, Haar and Gabor, have been investigated. Experiments results are reported to show that our method has very high correctness and extremely fast running speed. Based on this method we have developed a glasses detection system which can detect the glasses in facial images automatically.

Keywords

Haar transforms; face recognition; feature extraction; image classification; learning (artificial intelligence); object detection; table lookup; wavelet transforms; Gabor wavelet features; Haar wavelet features; boosting algorithm; facial images; glasses detection; image classifier; learning; look up table; real Adaboost; Artificial intelligence; Boosting; Computer science; Face detection; Face recognition; Glass; Image edge detection; Iterative algorithms; Radio access networks; Table lookup;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on

ISSN

1051-4651

Print_ISBN

0-7695-2128-2

Type

conf

DOI

10.1109/ICPR.2004.1334110

Filename

1334110