Improving visual search with image segmentation

  • Authors:
  • Clifton Forlines;Ravin Balakrishnan

  • Affiliations:
  • Mitsubishi Electric Research Labs, University of Toronto, Cambridge, USA;University of Toronto, Toronto, Canada

  • Venue:
  • Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
  • Year:
  • 2009

Quantified Score

Hi-index 0.01

Visualization

Abstract

People's ability to accurately locate target objects in images is severely affected by the prevalence of the sought objects. This negative effect greatly impacts critical real world tasks, such as baggage screening and cell slide pathology, in which target objects are rare. We present three novel image presentation techniques that are designed to improve visual search. Our techniques rely on the images being broken into image segments, which are then recombined or displayed in novel ways. The techniques and their underlying design reasoning are described in detail, and three experiments are presented that provide initial evidence that these techniques lead to better search performance in a simulated cell slide pathology task.