Frontal to profile face verification in the wild
Citations Over TimeTop 1% of 2016 papers
Abstract
We have collected a new face data set that will facilitate research in the problem of frontal to profile face verification `in the wild'. The aim of this data set is to isolate the factor of pose variation in terms of extreme poses like profile, where many features are occluded, along with other `in the wild' variations. We call this data set the Celebrities in Frontal-Profile (CFP) data set. We find that human performance on Frontal-Profile verification in this data set is only slightly worse (94.57% accuracy) than that on Frontal-Frontal verification (96.24% accuracy). However we evaluated many state-of-the-art algorithms, including Fisher Vector, Sub-SML and a Deep learning algorithm. We observe that all of them degrade more than 10% from Frontal-Frontal to Frontal-Profile verification. The Deep learning implementation, which performs comparable to humans on Frontal-Frontal, performs significantly worse (84.91% accuracy) on Frontal-Profile. This suggests that there is a gap between human performance and automatic face recognition methods for large pose variation in unconstrained images.
Related Papers
- → The Frontal Lobes(2003)22 cited
- → The Frontal Lobes(1993)12 cited
- → Learning and Memory in Baboons with Bilateral Lesions of Frontal or Inferotemporal Cortex(1967)16 cited
- The effect of oxysophoridine on electric activities and its power spectrums of cerebral frontal cortex in rats(2010)
- → MR Elastography of the Frontal Cortex: Impact of Aging and Regional Differences(2023)