Header menu link for other important links
X
Recognizing disguised faces: Human and machine evaluation
T.I. Dhamecha, , , A. Kumar
Published in Public Library of Science
2014
PMID: 25029188
Volume: 9
   
Issue: 7
Abstract
Face verification, though an easy task for humans, is a long-standing open research area. This is largely due to the challenging covariates, such as disguise and aging, which make it very hard to accurately verify the identity of a person. This paper investigates human and machine performance for recognizing/verifying disguised faces. Performance is also evaluated under familiarity and match/mismatch with the ethnicity of observers. The findings of this study are used to develop an automated algorithm to verify the faces presented under disguise variations. We use automatically localized feature descriptors which can identify disguised face patches and account for this information to achieve improved matching accuracy. The performance of the proposed algorithm is evaluated on the IIIT-Delhi Disguise database that contains images pertaining to 75 subjects with different kinds of disguise variations. The experiments suggest that the proposed algorithm can outperform a popular commercial system and evaluates them against humans in matching disguised face images. © 2014 Dhamecha et al.
CONTINUE READING
Figures & Tables (12)
  • Figure-0
    Figure 1. Illustrating the effect of disguise accessories ... Expand
  • Figure-1
    Table 1. Literature review.
  • Figure-2
    Figure 2. Sample questionnaire.
  • Figure-3
    Figure 3. Sample images from the ID V1 database.
  • Figure-4
    Figure 4. Distribution of genuine and impostor pairs ... Expand
  • Figure-5
    Table 4. p-values of statistical tests to understand the effect ... Expand
  • Figure-6
    Figure 5. Effect of disguising individual facials parts ... Expand
  • Figure-7
    Figure 6. Illustrating the steps involved in the proposed face ... Expand
  • 4 figures hidden
    Show all figures
About the journal
JournalPLoS ONE
PublisherPublic Library of Science
ISSN19326203