Complexion as a Soft Biometric in Human-Robot Interaction

Abstract

Complexion plays a remarkably important role in recognition. Experiments with human subjects have shown that complexion provides as much distinctiveness as other wellknown features such as the shape of the face. From the perspective an autonomous robot, changes in lighting (e.g. intensity, orientation) and camera parameters (e.g., white balance) can make capturing complexion challenging. In this paper, we evaluate complexion as a soft biometric using color (histograms) and texture (local binary patterns). We train a linear SVM to distinguish between the individual and impostors. We demonstrate the performance of this approach on a database of over 200 individuals collected to study biometrics in human-robot interaction. In our experiment we identify 9 individuals that interact with the robot on a regular basis, rejecting all others as unknown.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 01, 2013
Accession Number
ADA619041

Entities

People

  • Eric Martinson
  • J. G. Trafton
  • Wallace Lawson

Tags

DTIC Thesaurus Topics

  • Accuracy
  • Artificial Intelligence
  • Biometrics
  • Computer Vision
  • Detection
  • Fingerprint Recognition
  • Histograms
  • Human-Robot Interaction
  • Identification
  • Intensity
  • Kernel Functions
  • Military Research
  • Object Recognition
  • Pattern Recognition
  • Recognition
  • Robots
  • Supervised Machine Learning

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Regression Analysis.

Technology Areas

  • AI & ML
  • Autonomy