Comparison of two algorithms for 3D skin reconstruction

Authors:
Qian Zhang;Sung-Jong Eun;Taeg-Keun Whangbo
Affiliations:
Taishan University, Taian, China;Kyungwon University, Sujung-Gu, Songnam, Kyunggi-Do, Korea;Kyungwon University, Sujung-Gu, Songnam, Kyunggi-Do, Korea
Venue:
Proceedings of the 5th International Conference on Ubiquitous Information Management and Communication
Year:
2011

Citing 5
Cited 0

Multi-camera Scene Reconstruction via Graph Cuts

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Skin Texture Modeling

International Journal of Computer Vision - Special Issue on Texture Analysis and Synthesis
Stereo Correspondence by Dynamic Programming on a Tree

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Markov Random Field Modeling in Image Analysis

Markov Random Field Modeling in Image Analysis
Two stages stereo dense matching algorithm for 3d skin micro-surface reconstruction

MMM'10 Proceedings of the 16th international conference on Advances in Multimedia Modeling

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a study on 3D skin reconstruction based on image pairs is proposed. To recover 3D skin data from images, two different basic models were focused on. The first model was based on dense matching that combined the feature-based and region-based algorithms to propose a two-stage matching algorithm for a dense map. The second model was based on the Markov Random Field (MRF) model that formulated the problem of 3D reconstruction as a Bayes decision task. It was found that one model is more effective for its corresponding skin texture type. Cross-experiments were done to test the two models with the images that the authors' took. The analysis and comparison are summarized in the algorithms for 3D skin reconstruction.