Skin surface reconstruction from stereo images

  • Authors:
  • Qian Zhang;TaegKeun Whangbo

  • Affiliations:
  • Kyungwon University, Sujung-Gu, Songnam, Kyunggi-Do, Korea;Kyungwon University, Sujung-Gu, Songnam, Kyunggi-Do, Korea

  • Venue:
  • Proceedings of the 4th International Conference on Uniquitous Information Management and Communication
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

A novel stereo matching algorithm for skin surface reconstruction is proposed in the paper. Wrinkles are distributed on the skin to form a grid which is the feature for stereo matching. Test results show that most matched points by feature extraction algorithms such as corner detection lie on the wrinkle grid. Skin images taken by two cameras together differ slightly due to the light influence. The architecture is based on the image segmentation, taking into account skin properties. Graph cut algorithm is used for skin segmentation, and an improved region based algorithm is used for dense matching. We compare and evaluate our stereo results with respect to other proposed algorithms with our test images.