期刊
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
卷 6, 期 4, 页码 1275-1286出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIFS.2011.2159205
关键词
Face verification; labeled faces in the wild (LFW); locally adaptive regression kernels (LARKs); matrix cosine similarity; one-shot similarity (OSS)
资金
- AFOSR [FA 9550-07-01-0365]
- NSF [CCF-1016018]
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据