Title
Gaussian Weak Classifiers Based on Haar-Like Features with Four Rectangles for Real-time Face Detection
Abstract
This paper proposes Gaussian weak classifiers (GWCs) for use in real-time face detection systems. GWCs are based on Haar-like features (HFs) with four rectangles (HF4s), which constitute the majority of the HFs used to train a face detector. To label an image as face or clutter (non-face), GWC uses the responses of the two HF2s in a HF4 to compute a Mahalanobis distance which is later compared to a threshold to make decisions. For a fixed accuracy on the face class, GWCs can classify clutter images with more accuracy than the existing weak classifier types. Our experiments compare the accuracy and speed of the face detectors built with four different weak classifier types: GWCs, Viola & Jones's, Rasolzadeh et al.'s and Mita et al.'s. On the standard MIT+CMU image database, the GWC-based face detector provided 40% less false positives and required 32% less time for the scanning process when compared to the detector that used Viola & Jones's weak classifiers. When compared to detectors that used Rasolzadeh et al.'s and Mita et al.'s weak classifiers, the GWC-based detector produced 11% and 9% fewer false positives. Simultaneously, it required 37% and 42% less time for the scanning process.
Year
DOI
Venue
2009
10.1007/978-3-642-03767-2_11
CAIP
Keywords
Field
DocType
real-time face detection system,gwc-based detector,haar-like features,gaussian weak,face class,weak classifier,fixed accuracy,existing weak classifier type,different weak classifier type,gwc-based face detector,gaussian weak classifier,face detector,real-time face detection,false positive,real time,mahalanobis distance,face detection
Computer vision,Pattern recognition,Computer science,Clutter,Mahalanobis distance,Haar-like features,Gaussian,Artificial intelligence,Face detection,Classifier (linguistics),Detector,False positive paradox
Conference
Volume
ISSN
Citations 
5702
0302-9743
2
PageRank 
References 
Authors
0.39
10
3
Name
Order
Citations
PageRank
Sri-Kaushik Pavani11498.30
David Delgado Gomez2629.67
Alejandro F. Frangi34333309.21