Paper Info
Title
Automated facial feature detection and face recognition using Gabor features on range and portrait images
Abstract
In this paper, we present a novel identity verification sys- tem based on Gabor features extracted from range (3D) repre- sentations of faces. Multiple landmarks (fiducials) on a face are automatically detected using these Gabor features. Once the landmarks are identified, the Gabor features on all fidu- cials of a face are concatenated to form a feature vector for that particular face. Linear discriminant analysis (LDA) is used to reduce the dimensionality of the feature vector while maximizing the discrimination power. These novel features were tested on 1196 range images. The same features were also extracted from portrait images, and the accuracies of both modalities were compared. A superior verification accuracy was obtained using the range data, and a highly competitive accuracy to that of other techniques in the literature was also obtained for the portrait data.
Year
DOI
Venue
2008
10.1109/ICIP.2008.4712368
San Diego, CA
Keywords
Field
DocType
Gabor filters,face recognition,feature extraction,image representation,decoded video sequences,packet losses,perceptual quality,saliency-based objective quality assessment metric,subjective scores,visual saliency,weighting method,Biometry,Face recognition,Gabor wavelets,Range images
Computer vision,Facial recognition system,Feature vector,Fiducial marker,Pattern recognition,Gabor wavelet,Computer science,Feature extraction,Curse of dimensionality,Artificial intelligence,Pixel,Linear discriminant analysis
Conference
ISSN
ISBN
Citations 
1522-4880 E-ISBN : 978-1-4244-1764-3
978-1-4244-1764-3
6
PageRank 
References 
Authors
0.49
6
4
Name
Order
Citations
PageRank
Sina Jahanbin1372.58
Hyohoon Choi2595.37
Rana Jahanbin3100.91
Alan C. Bovik45062349.55