A system of clothes matching for visually impaired persons

  • Authors:
  • Shuai Yuan

  • Affiliations:
  • The City College of New York, New York City, NY, USA

  • Venue:
  • Proceedings of the 12th international ACM SIGACCESS conference on Computers and accessibility
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Choosing clothes is a challenge task for blind people. In this paper, we propose a proof of concept system to match a pair of image from different clothes for both pattern and color. Our system consists of 1) a camera and a computer to perform color detection, pattern and color matching process; 2) supporting speech commands to flexibly control and configure; and 3) audio feedbacks to provide matching results of both color and pattern. The system can deal with clothes in uniform color without any pattern, as well as clothes with multiple colors and complex patterns. Furthermore, our method is robust to variations of illumination, clothes rotation, and clothes wrinkles. The proposed method is evaluated on two challenge databases of clothes. Experimental results demonstrate the robustness and effectiveness on clothes matching.