Automatic selection of ROI in multispectral imaging of CMS

DOI

10.2991/icmt-13.2013.194How to use a DOI?

Keywords

Multispectral Imaging; Chinese medicine slices; Image Segmentation.

Abstract

the multispectral imaging used in identification of Chinese medicine slices (CMS) can identify the authenticity of CMS and evaluate their quality by comparing the characteristic spectral curve from spectral cube. In order to apply multispectral imaging to actual application of CMS identification. Automatically extracting the region of interest (ROI) is necessary. A new algorithm for image segmentation is presented. A mask exactly extracting RIO of the multispectral images is generated by the computer automatically by employing the method. Multispectral imaging experiments with American ginseng and pilose antler were conducted, and the result showed more than 95% of the ROI was extracted using the new algorithm for image segmentation.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Heng Zhang
AU  - Cuiying Hu
AU  - Qingxia Meng
AU  - Jing Zhao
PY  - 2013/11
DA  - 2013/11
TI  - Automatic selection of ROI in multispectral imaging of CMS
BT  - Proceedings of 3rd International Conference on Multimedia Technology(ICMT-13)
PB  - Atlantis Press
SP  - 1589
EP  - 1596
SN  - 1951-6851
UR  - https://doi.org/10.2991/icmt-13.2013.194
DO  - 10.2991/icmt-13.2013.194
ID  - Zhang2013/11
ER  -