arrow
Volume 8, Issue 4
3D Garment Segmentation Based on Semi-supervised Learning Method

Mian Huang, Li Liu, Ruomei Wang, Xiaodong Fu & Lijun Liu

Journal of Fiber Bioengineering & Informatics, 8 (2015), pp. 657-665.

Published online: 2015-08

Export citation
  • 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.
  • Keywords

Semi-supervised Segmentation Co-analysis Conditional Random Field 3D Garments

  • AMS Subject Headings

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{JFBI-8-657, author = {}, title = {3D Garment Segmentation Based on Semi-supervised Learning Method}, journal = {Journal of Fiber Bioengineering and Informatics}, year = {2015}, volume = {8}, number = {4}, pages = {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.}, issn = {2617-8699}, doi = {https://doi.org/10.3993/jfbim00174}, url = {http://global-sci.org/intro/article_detail/jfbi/4747.html} }
TY - JOUR T1 - 3D Garment Segmentation Based on Semi-supervised Learning Method JO - Journal of Fiber Bioengineering and Informatics VL - 4 SP - 657 EP - 665 PY - 2015 DA - 2015/08 SN - 8 DO - http://doi.org/10.3993/jfbim00174 UR - https://global-sci.org/intro/article_detail/jfbi/4747.html KW - Semi-supervised KW - Segmentation KW - Co-analysis KW - Conditional Random Field KW - 3D Garments AB - 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.
Mian Huang, Li Liu, Ruomei Wang, Xiaodong Fu & Lijun Liu. (2019). 3D Garment Segmentation Based on Semi-supervised Learning Method. Journal of Fiber Bioengineering and Informatics. 8 (4). 657-665. doi:10.3993/jfbim00174
Copy to clipboard
The citation has been copied to your clipboard