Abstract | ||
---|---|---|
In this paper, we propose a new discriminative multimetric learning method for kinship verification via facial image analysis. Given each face image, we first extract multiple features using different face descriptors to characterize face images from different aspects because different feature descriptors can provide complementary information. Then, we jointly learn multiple distance metrics with these extracted multiple features under which the probability of a pair of face image with a kinship relation having a smaller distance than that of the pair without a kinship relation is maximized, and the correlation of different features of the same face sample is maximized, simultaneously, so that complementary and discriminative information is exploited for verification. Experimental results on four face kinship data sets show the effectiveness of our proposed method over the existing single-metric and multimetric learning methods. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/TIFS.2014.2327757 | IEEE Transactions on Information Forensics and Security |
Keywords | Field | DocType |
face recognition,feature descriptors,multiple distance metrics,multi-metric learning,learning (artificial intelligence),single-metric learning method,face descriptors,multiple feature extraction,discriminative learning,kinship verification,feature extraction,face image pair probability,biometrics,discriminative multimetric learning method,face image characterization,face kinship data sets,facial image analysis,probability,face,learning artificial intelligence,correlation,data mining,measurement | Data set,Pattern recognition,Kinship,Computer science,Feature extraction,Correlation,Artificial intelligence,Discriminative model,Machine learning | Journal |
Volume | Issue | ISSN |
9 | 7 | 1556-6013 |
Citations | PageRank | References |
54 | 1.07 | 23 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Haibin Yan | 1 | 54 | 1.07 |
Jiwen Lu | 2 | 3105 | 153.88 |
Weihong Deng | 3 | 1162 | 77.22 |
Xiuzhuang Zhou | 4 | 380 | 20.26 |