3D Garment Segmentation Based on Semi-supervised Learning Method

3D Garment Segmentation Based on Semi-supervised Learning Method

Year:    2015

Journal of Fiber Bioengineering and Informatics, Vol. 8 (2015), Iss. 4 : pp. 657–665

Abstract

In this paper, we propose a semi-supervised learning method to simultaneous segmentation and labeling of parts in 3D garments. The key idea in this work is to analyze 3D garments using semi-supervised learning method which can label parts in various 3D garments. We first develop an objective function based on Conditional Random Field (CRF) model to learn the prior knowledge of garment components from a set of training examples. Then, we exploit an effective training method that utilizes JointBoost classifiers based on the co-analysis for garments. And we modify the JointBoost to automatically cluster the segmented components without requiring manual parameter tuning. The purpose of our method is to relieve the manual segmentation and labeling of components in 3D garment collections. Finally, the experimental results show the performance of our proposed method is effective.

You do not have full access to this article.

Already a Subscriber? Sign in as an individual or via your institution

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.3993/jfbim00174

Journal of Fiber Bioengineering and Informatics, Vol. 8 (2015), Iss. 4 : pp. 657–665

Published online:    2015-01

AMS Subject Headings:   

Copyright:    COPYRIGHT: © Global Science Press

Pages:    9

Keywords:    Semi-supervised