articleMar 1, 2016Closed access

Frontal to profile face verification in the wild

SSSoumyadip SenguptaJCJun-Cheng ChenCDCarlos D. CastilloVMVishal M. PatelRCRama Chellappa

University of Maryland, College Park · Rutgers, The State University of New Jersey

Indexed incrossref

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…

Citation impact

796
total citations
FWCI
17.74
Percentile
100%
References
46
Citations per year

Authors

6

Topics & keywords

Topics
Keywords
  • Artificial intelligence
  • Face (sociological concept)
  • Computer science
  • Pattern recognition (psychology)
  • Set (abstract data type)
  • Data set
  • Variation (astronomy)
  • Facial recognition system
No related works found for this paper.

Funding