December 2022
Volume 22, Issue 14
Open Access
Vision Sciences Society Annual Meeting Abstract  |   December 2022
Comparing Human and Deep Convolutional Neural Network Performance on Twin Identification
Author Affiliations & Notes
  • Connor J. Parde
    The University of Texas at Dallas
  • Ginni Strehle
    The University of Texas at Dallas
  • Vivekjyoti Banerjee
    University of Maryland
  • Ying Hu
    The University of Texas at Dallas
  • Jacqueline G. Cavazos
    University of California Irvine
  • Carlos D. Castillo
    Johns Hopkins University
  • Alice J. O'Toole
    The University of Texas at Dallas
  • Footnotes
    Acknowledgements  Funded by the National Eye Institute (NEI)
Journal of Vision December 2022, Vol.22, 3357. doi:https://doi.org/10.1167/jov.22.14.3357
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Connor J. Parde, Ginni Strehle, Vivekjyoti Banerjee, Ying Hu, Jacqueline G. Cavazos, Carlos D. Castillo, Alice J. O'Toole; Comparing Human and Deep Convolutional Neural Network Performance on Twin Identification. Journal of Vision 2022;22(14):3357. https://doi.org/10.1167/jov.22.14.3357.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Deep convolutional neural networks (DCNNs) have achieved human-level accuracy in face identification (Phillips et al., 2018), though it is unclear how accurately they discriminate highly similar faces. Here, we compared human and DCNN performance on a challenging face-identification task that includes identical twins. Participants (N=29) completed a face identification task in which they viewed pairs of high-quality, frontal images in three conditions: match (same identity, N=40), general imposter (different identities from similar demographic groups, N=40), and twin imposter (identical twin siblings, N=40). Ratings were collected on a 5-point Likert scale (1: sure different; 5: sure same). Performance was assessed for a DCNN trained for face identification (Ranjan et al., 2018) on the same image pairs used in the human experiment. Human and DCNN identification accuracy were measured using the area under the ROC curve (AUC). DCNN performance was similar to human performance when comparing the AUC for match pairs versus general-imposter pairs (human AUC=0.97, DCNN AUC=1.0). When comparing match pairs versus twin-imposter pairs, human performance declined substantially (AUC=0.79), but DCNN accuracy remained high (AUC=0.96). Human participants’ performance in the general-imposter condition correlated strongly with their performance in the twin-imposter condition (r=0.64). Next, we conducted an item analysis to examine the similarity of each image pair for both human participants and the DCNN. Rank-order correlation of these trials showed moderate correlation between human and DCNN rankings for match (⍴=0.50, p<0.001) and twin imposter (⍴=0.48, p<0.01) pairs, and no correlation for general imposter pairs. In conclusion, the DCNN outperformed human participants when distinguishing face images of identical twins. However, the relative difficulty of identifying high-resemblance faces was related across DCNNs and humans. This study provides insight into the accuracy of humans and DCNNs when discriminating high-resemblance face identities.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×