Shape Reconstruction of Skin Surface from Shading Images Using Simulated Annealing - Robotics Institute Carnegie Mellon University

Shape Reconstruction of Skin Surface from Shading Images Using Simulated Annealing

Hideo Saito, Y. Somiya, and S. Ozawa
Conference Paper, Proceedings of 2nd Asian Conference on Computer Vision (ACCV '95), Vol. 3, pp. 348 - 352, December, 1995

Abstract

This paper describes about a new method for reconstructing a shape of a skin surface replica from three shading images taken with three different lightings. Since the shading images include shadows caused by surface height fluctuation, the conventional photometric stereo method is not suitable for reconstructing its surface shape. In the proposed method, the evaluation function of the surface shape is defined in consideration of the effects of shadow, then the shape is reconstructed by optimizing the evaluation using simulated annealing. The experiments to reconstruct the shape from synthesized images and real images demonstrate that the proposed method is effective for shape reconstruction from shading images which include shadows.

BibTeX

@conference{Saito-1995-14044,
author = {Hideo Saito and Y. Somiya and S. Ozawa},
title = {Shape Reconstruction of Skin Surface from Shading Images Using Simulated Annealing},
booktitle = {Proceedings of 2nd Asian Conference on Computer Vision (ACCV '95)},
year = {1995},
month = {December},
volume = {3},
pages = {348 - 352},
}