Title: Using Gaussian mixture model to fix errors in SFS approach based on propagation

Authors: Wenmin Huang; Jiquan Ma

Addresses: College of Computer Science and Technology, Heilongjiang University, China ' Key Laboratory of Database and Parallel Computing of Heilongjiang Province, College of Computer Science and Technology, Heilongjiang University, No. 74 R. Xuefu Nangang District, Harbin, Hei Longjiang Province, 150080, China

Abstract: A new Gaussian mixture model is used to improve the quality of propagation method for SFS in this paper. The improved algorithm can overcome most difficulties of propagation SFS method including slow convergence, interdependence of propagation nodes and error accumulation. For slow convergence and interdependence of propagation nodes, stable propagation source and integration path are used to make sure that the reconstruction work of each pixel in the image is independent. A Gaussian mixture model based on prior conditions has been proposed to fix the error of integration. Good result has achieved in the experiment for Lambert composite image of front illumination.

Keywords: shape from shading; propagation method; silhouette; Gaussian mixture model; surface reconstruction.

DOI: 10.1504/IJCSE.2019.101885

International Journal of Computational Science and Engineering, 2019 Vol.19 No.4, pp.570 - 580

Received: 29 Jul 2016
Accepted: 09 Jan 2017

Published online: 27 Aug 2019 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article