ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Local higher-order statistics (LHS) for texture categorization and facial analysis
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
Force work induced metric for face verification
IScIDE'12 Proceedings of the third Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
Discriminative dictionary learning with pairwise constraints
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Learning discriminant face descriptor for face recognition
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part II
Block LBP displacement based local matching approach for human face recognition
ACCV'12 Proceedings of the 11th international conference on Computer Vision - Volume Part I
Face recognition for web-scale datasets
Computer Vision and Image Understanding
| Hi-index | 0.00 |
We present a novel face representation based on locally adaptive regression kernel (LARK) descriptors. Our LARK descriptor measures a self-similarity based on “signal-induced distance” between a center pixel and surrounding pixels in a local neighborhood. By applying principal component analysis (PCA) and a logistic function to LARK consecutively, we develop a new binary-like face representation which achieves state-of-the-art face verification performance on the challenging benchmark “Labeled Faces in the Wild” (LFW) dataset. In the case where training data are available, we employ one-shot similarity (OSS) based on linear discriminant analysis (LDA). The proposed approach achieves state-of-the-art performance on both the unsupervised setting and the image restrictive training setting (72.23% and 78.90% verification rates), respectively, as a single descriptor representation, with no preprocessing step. As opposed to combined 30 distances which achieve 85.13%, we achieve comparable performance (85.1%) with only 14 distances while significantly reducing computational complexity.