Title
Gabor-based gradient orientation pyramid for kinship verification under uncontrolled environments
Abstract
This paper presents a Gabor-based Gradient Orientation Pyramid (GGOP) feature representation method for kinship verification from facial images. First, we perform Gabor wavelet on each face image to obtain a set of Gabor magnitude (GM) feature images from different scales and orientations. Then, we extract the Gradient Orientation Pyramid (GOP) feature of each GM feature image and perform multiple feature fusion for kinship verification. When combined with the discriminative support vector machine (SVM) classifier, GGOP demonstrates the best performance in our experiments, in comparison with several state-of-the-art face feature descriptors. Experimental results are presented to show the efficacy of our proposed approach. Moreover, the performance of our proposed method is also comparable to that of human observers.
Year
DOI
Venue
2012
10.1145/2393347.2396297
ACM Multimedia 2001
Keywords
Field
DocType
feature representation method,gabor wavelet,gabor-based gradient orientation pyramid,uncontrolled environment,gm feature image,state-of-the-art face feature descriptors,feature image,gradient orientation pyramid,gabor magnitude,kinship verification,multiple feature fusion,image descriptors
Computer vision,Feature fusion,Pattern recognition,Kinship,Computer science,Gabor wavelet,Support vector machine,Artificial intelligence,Visual descriptors,Pyramid,Classifier (linguistics),Discriminative model
Conference
Citations 
PageRank 
References 
39
1.00
10
Authors
4
Name
Order
Citations
PageRank
Xiuzhuang Zhou138020.26
Jiwen Lu23105153.88
Junlin Hu327511.07
Yuanyuan Shang4403.04