IEICE TRANSACTIONS on Information
Automatic Recognition of Mycobacterium Tuberculosis Based on Active Shape Model
Summary :
This paper realized the automatic recognition of Mycobacterium tuberculosis in Ziehl-Neelsen stained images by the conventional light microscopy, which can be used in the computer-aided diagnosis of the tuberculosis. We proposed a novel recognition method based on active shape model. First, the candidate bacillus objects are segmented by a method of marker-based watershed transform. Next, a point distribution model of the object shape is proposed to label the landmarks on the object automatically. Then the active shape model is performed after aligning the training set with a weight matrix. The deformation regulation of the object shape is discovered and successfully applied in recognition without using geometric and other commonly used features. During this process, a width consistency constraint is combined with the shape parameter to improve the accuracy of the recognition. Experimental results demonstrate that the proposed method yields high accuracy in the images with different background colors. The recognition accuracy in object level and image level are 92.37% and 97.91% respectively.
- Publication
- IEICE TRANSACTIONS on Information Vol.E99-D No.4 pp.1162-1171
- Publication Date
- 2016/04/01
- Publicized
- 2016/01/08
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2015EDP7253
- Type of Manuscript
- PAPER
- Category
- Pattern Recognition
Authors
Chao XU
National University of Defense Technology
Dongxiang ZHOU
National University of Defense Technology
Tao GUAN
National University of Defense Technology
Yongping ZHAI
National University of Defense Technology
Yunhui LIU
The Chinese University of Hong Kong
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Chao XU, Dongxiang ZHOU, Tao GUAN, Yongping ZHAI, Yunhui LIU, "Automatic Recognition of Mycobacterium Tuberculosis Based on Active Shape Model" in IEICE TRANSACTIONS on Information,
vol. E99-D, no. 4, pp. 1162-1171, April 2016, doi: 10.1587/transinf.2015EDP7253.
Abstract: This paper realized the automatic recognition of Mycobacterium tuberculosis in Ziehl-Neelsen stained images by the conventional light microscopy, which can be used in the computer-aided diagnosis of the tuberculosis. We proposed a novel recognition method based on active shape model. First, the candidate bacillus objects are segmented by a method of marker-based watershed transform. Next, a point distribution model of the object shape is proposed to label the landmarks on the object automatically. Then the active shape model is performed after aligning the training set with a weight matrix. The deformation regulation of the object shape is discovered and successfully applied in recognition without using geometric and other commonly used features. During this process, a width consistency constraint is combined with the shape parameter to improve the accuracy of the recognition. Experimental results demonstrate that the proposed method yields high accuracy in the images with different background colors. The recognition accuracy in object level and image level are 92.37% and 97.91% respectively.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2015EDP7253/_p
Copy
@ARTICLE{e99-d_4_1162,
author={Chao XU, Dongxiang ZHOU, Tao GUAN, Yongping ZHAI, Yunhui LIU, },
journal={IEICE TRANSACTIONS on Information},
title={Automatic Recognition of Mycobacterium Tuberculosis Based on Active Shape Model},
year={2016},
volume={E99-D},
number={4},
pages={1162-1171},
abstract={This paper realized the automatic recognition of Mycobacterium tuberculosis in Ziehl-Neelsen stained images by the conventional light microscopy, which can be used in the computer-aided diagnosis of the tuberculosis. We proposed a novel recognition method based on active shape model. First, the candidate bacillus objects are segmented by a method of marker-based watershed transform. Next, a point distribution model of the object shape is proposed to label the landmarks on the object automatically. Then the active shape model is performed after aligning the training set with a weight matrix. The deformation regulation of the object shape is discovered and successfully applied in recognition without using geometric and other commonly used features. During this process, a width consistency constraint is combined with the shape parameter to improve the accuracy of the recognition. Experimental results demonstrate that the proposed method yields high accuracy in the images with different background colors. The recognition accuracy in object level and image level are 92.37% and 97.91% respectively.},
keywords={},
doi={10.1587/transinf.2015EDP7253},
ISSN={1745-1361},
month={April},}
Copy
TY - JOUR
TI - Automatic Recognition of Mycobacterium Tuberculosis Based on Active Shape Model
T2 - IEICE TRANSACTIONS on Information
SP - 1162
EP - 1171
AU - Chao XU
AU - Dongxiang ZHOU
AU - Tao GUAN
AU - Yongping ZHAI
AU - Yunhui LIU
PY - 2016
DO - 10.1587/transinf.2015EDP7253
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2016
AB - This paper realized the automatic recognition of Mycobacterium tuberculosis in Ziehl-Neelsen stained images by the conventional light microscopy, which can be used in the computer-aided diagnosis of the tuberculosis. We proposed a novel recognition method based on active shape model. First, the candidate bacillus objects are segmented by a method of marker-based watershed transform. Next, a point distribution model of the object shape is proposed to label the landmarks on the object automatically. Then the active shape model is performed after aligning the training set with a weight matrix. The deformation regulation of the object shape is discovered and successfully applied in recognition without using geometric and other commonly used features. During this process, a width consistency constraint is combined with the shape parameter to improve the accuracy of the recognition. Experimental results demonstrate that the proposed method yields high accuracy in the images with different background colors. The recognition accuracy in object level and image level are 92.37% and 97.91% respectively.
ER -
English
