Surface Defect Detection on Optical Devices based on Microscopic Dark-Field Scattering Imaging

2389 Views
2253 Downloads
Export citation: ABNT
YIN, Yingjie ;XU, De ;ZHANG, Zhengtao ;BAI, Mingran ;ZHANG, Feng ;TAO, Xian ;WANG, Xingang .
Surface Defect Detection on Optical Devices based on Microscopic Dark-Field Scattering Imaging. 
Strojniški vestnik - Journal of Mechanical Engineering, [S.l.], v. 61, n.1, p. 24-32, june 2018. 
ISSN 0039-2480.
Available at: <https://www.sv-jme.eu/article/surface-defect-detection-on-optical-devices-based-on-microscopic-dark-field-scattering-imaging/>. Date accessed: 08 oct. 2024. 
doi:http://dx.doi.org/10.5545/sv-jme.2014.1644.
Yin, Y., Xu, D., Zhang, Z., Bai, M., Zhang, F., Tao, X., & Wang, X.
(2015).
Surface Defect Detection on Optical Devices based on Microscopic Dark-Field Scattering Imaging.
Strojniški vestnik - Journal of Mechanical Engineering, 61(1), 24-32.
doi:http://dx.doi.org/10.5545/sv-jme.2014.1644
@article{sv-jmesv-jme.2014.1644,
	author = {Yingjie  Yin and De  Xu and Zhengtao  Zhang and Mingran  Bai and Feng  Zhang and Xian  Tao and Xingang  Wang},
	title = {Surface Defect Detection on Optical Devices based on Microscopic Dark-Field Scattering Imaging},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {61},
	number = {1},
	year = {2015},
	keywords = {SIFT, LDF, cluster algorithm, image segmentation, image mosaic, dark-field imaging, optical devices},
	abstract = {Methods of surface defect detection on optical devices are proposed in this paper. First, a series of microscopic dark-field scattering images were collected with a line-scan camera. Translation transformation between overlaps of adjacent microscopic dark-field scattering images resulted from the line-scan camera’s imaging feature. An image mosaic algorithm based on scale invariance feature transform (SIFT) is proposed to stitch dark-field images collected by the line-scan camera. SIFT feature matching point-pairs were extracted from regions of interest in the adjacent microscopic dark-field scattering images. The best set of SIFT feature matching point-pairs was obtained via a parallel clustering algorithm. The transformation matrix of the two images was calculated by the best matching point-pair set, and then image stitching was completed through transformation matrix. Secondly, a sample threshold segmentation method was used to segment dark-field images that were previously stitched together because the image background was very dark. Finally, four different supervised learning classifiers are used to classify the defect represented by a six-dimensional feature vector by shape (point or line), and the performance of linear discriminant function (LDF) classifier is demonstrated to be the best. The experimental results showed that defects on optical devices could be detected efficiently by the proposed methods.},
	issn = {0039-2480},	pages = {24-32},	doi = {10.5545/sv-jme.2014.1644},
	url = {https://www.sv-jme.eu/article/surface-defect-detection-on-optical-devices-based-on-microscopic-dark-field-scattering-imaging/}
}
Yin, Y.,Xu, D.,Zhang, Z.,Bai, M.,Zhang, F.,Tao, X.,Wang, X.
2015 June 61. Surface Defect Detection on Optical Devices based on Microscopic Dark-Field Scattering Imaging. Strojniški vestnik - Journal of Mechanical Engineering. [Online] 61:1
%A Yin, Yingjie 
%A Xu, De 
%A Zhang, Zhengtao 
%A Bai, Mingran 
%A Zhang, Feng 
%A Tao, Xian 
%A Wang, Xingang 
%D 2015
%T Surface Defect Detection on Optical Devices based on Microscopic Dark-Field Scattering Imaging
%B 2015
%9 SIFT, LDF, cluster algorithm, image segmentation, image mosaic, dark-field imaging, optical devices
%! Surface Defect Detection on Optical Devices based on Microscopic Dark-Field Scattering Imaging
%K SIFT, LDF, cluster algorithm, image segmentation, image mosaic, dark-field imaging, optical devices
%X Methods of surface defect detection on optical devices are proposed in this paper. First, a series of microscopic dark-field scattering images were collected with a line-scan camera. Translation transformation between overlaps of adjacent microscopic dark-field scattering images resulted from the line-scan camera’s imaging feature. An image mosaic algorithm based on scale invariance feature transform (SIFT) is proposed to stitch dark-field images collected by the line-scan camera. SIFT feature matching point-pairs were extracted from regions of interest in the adjacent microscopic dark-field scattering images. The best set of SIFT feature matching point-pairs was obtained via a parallel clustering algorithm. The transformation matrix of the two images was calculated by the best matching point-pair set, and then image stitching was completed through transformation matrix. Secondly, a sample threshold segmentation method was used to segment dark-field images that were previously stitched together because the image background was very dark. Finally, four different supervised learning classifiers are used to classify the defect represented by a six-dimensional feature vector by shape (point or line), and the performance of linear discriminant function (LDF) classifier is demonstrated to be the best. The experimental results showed that defects on optical devices could be detected efficiently by the proposed methods.
%U https://www.sv-jme.eu/article/surface-defect-detection-on-optical-devices-based-on-microscopic-dark-field-scattering-imaging/
%0 Journal Article
%R 10.5545/sv-jme.2014.1644
%& 24
%P 9
%J Strojniški vestnik - Journal of Mechanical Engineering
%V 61
%N 1
%@ 0039-2480
%8 2018-06-27
%7 2018-06-27
Yin, Yingjie, De  Xu, Zhengtao  Zhang, Mingran  Bai, Feng  Zhang, Xian  Tao, & Xingang  Wang.
"Surface Defect Detection on Optical Devices based on Microscopic Dark-Field Scattering Imaging." Strojniški vestnik - Journal of Mechanical Engineering [Online], 61.1 (2015): 24-32. Web.  08 Oct. 2024
TY  - JOUR
AU  - Yin, Yingjie 
AU  - Xu, De 
AU  - Zhang, Zhengtao 
AU  - Bai, Mingran 
AU  - Zhang, Feng 
AU  - Tao, Xian 
AU  - Wang, Xingang 
PY  - 2015
TI  - Surface Defect Detection on Optical Devices based on Microscopic Dark-Field Scattering Imaging
JF  - Strojniški vestnik - Journal of Mechanical Engineering
DO  - 10.5545/sv-jme.2014.1644
KW  - SIFT, LDF, cluster algorithm, image segmentation, image mosaic, dark-field imaging, optical devices
N2  - Methods of surface defect detection on optical devices are proposed in this paper. First, a series of microscopic dark-field scattering images were collected with a line-scan camera. Translation transformation between overlaps of adjacent microscopic dark-field scattering images resulted from the line-scan camera’s imaging feature. An image mosaic algorithm based on scale invariance feature transform (SIFT) is proposed to stitch dark-field images collected by the line-scan camera. SIFT feature matching point-pairs were extracted from regions of interest in the adjacent microscopic dark-field scattering images. The best set of SIFT feature matching point-pairs was obtained via a parallel clustering algorithm. The transformation matrix of the two images was calculated by the best matching point-pair set, and then image stitching was completed through transformation matrix. Secondly, a sample threshold segmentation method was used to segment dark-field images that were previously stitched together because the image background was very dark. Finally, four different supervised learning classifiers are used to classify the defect represented by a six-dimensional feature vector by shape (point or line), and the performance of linear discriminant function (LDF) classifier is demonstrated to be the best. The experimental results showed that defects on optical devices could be detected efficiently by the proposed methods.
UR  - https://www.sv-jme.eu/article/surface-defect-detection-on-optical-devices-based-on-microscopic-dark-field-scattering-imaging/
@article{{sv-jme}{sv-jme.2014.1644},
	author = {Yin, Y., Xu, D., Zhang, Z., Bai, M., Zhang, F., Tao, X., Wang, X.},
	title = {Surface Defect Detection on Optical Devices based on Microscopic Dark-Field Scattering Imaging},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {61},
	number = {1},
	year = {2015},
	doi = {10.5545/sv-jme.2014.1644},
	url = {https://www.sv-jme.eu/article/surface-defect-detection-on-optical-devices-based-on-microscopic-dark-field-scattering-imaging/}
}
TY  - JOUR
AU  - Yin, Yingjie 
AU  - Xu, De 
AU  - Zhang, Zhengtao 
AU  - Bai, Mingran 
AU  - Zhang, Feng 
AU  - Tao, Xian 
AU  - Wang, Xingang 
PY  - 2018/06/27
TI  - Surface Defect Detection on Optical Devices based on Microscopic Dark-Field Scattering Imaging
JF  - Strojniški vestnik - Journal of Mechanical Engineering; Vol 61, No 1 (2015): Strojniški vestnik - Journal of Mechanical Engineering
DO  - 10.5545/sv-jme.2014.1644
KW  - SIFT, LDF, cluster algorithm, image segmentation, image mosaic, dark-field imaging, optical devices
N2  - Methods of surface defect detection on optical devices are proposed in this paper. First, a series of microscopic dark-field scattering images were collected with a line-scan camera. Translation transformation between overlaps of adjacent microscopic dark-field scattering images resulted from the line-scan camera’s imaging feature. An image mosaic algorithm based on scale invariance feature transform (SIFT) is proposed to stitch dark-field images collected by the line-scan camera. SIFT feature matching point-pairs were extracted from regions of interest in the adjacent microscopic dark-field scattering images. The best set of SIFT feature matching point-pairs was obtained via a parallel clustering algorithm. The transformation matrix of the two images was calculated by the best matching point-pair set, and then image stitching was completed through transformation matrix. Secondly, a sample threshold segmentation method was used to segment dark-field images that were previously stitched together because the image background was very dark. Finally, four different supervised learning classifiers are used to classify the defect represented by a six-dimensional feature vector by shape (point or line), and the performance of linear discriminant function (LDF) classifier is demonstrated to be the best. The experimental results showed that defects on optical devices could be detected efficiently by the proposed methods.
UR  - https://www.sv-jme.eu/article/surface-defect-detection-on-optical-devices-based-on-microscopic-dark-field-scattering-imaging/
Yin, Yingjie, Xu, De, Zhang, Zhengtao, Bai, Mingran, Zhang, Feng, Tao, Xian, AND Wang, Xingang.
"Surface Defect Detection on Optical Devices based on Microscopic Dark-Field Scattering Imaging" Strojniški vestnik - Journal of Mechanical Engineering [Online], Volume 61 Number 1 (27 June 2018)

Authors

Affiliations

  • Chinese Academy of Sciences, Institute of Automation, Research Center of Precision Sensing and Control, China 1

Paper's information

Strojniški vestnik - Journal of Mechanical Engineering 61(2015)1, 24-32
© The Authors, CC-BY 4.0 Int. Change in copyright policy from 2022, Jan 1st.

https://doi.org/10.5545/sv-jme.2014.1644

Methods of surface defect detection on optical devices are proposed in this paper. First, a series of microscopic dark-field scattering images were collected with a line-scan camera. Translation transformation between overlaps of adjacent microscopic dark-field scattering images resulted from the line-scan camera’s imaging feature. An image mosaic algorithm based on scale invariance feature transform (SIFT) is proposed to stitch dark-field images collected by the line-scan camera. SIFT feature matching point-pairs were extracted from regions of interest in the adjacent microscopic dark-field scattering images. The best set of SIFT feature matching point-pairs was obtained via a parallel clustering algorithm. The transformation matrix of the two images was calculated by the best matching point-pair set, and then image stitching was completed through transformation matrix. Secondly, a sample threshold segmentation method was used to segment dark-field images that were previously stitched together because the image background was very dark. Finally, four different supervised learning classifiers are used to classify the defect represented by a six-dimensional feature vector by shape (point or line), and the performance of linear discriminant function (LDF) classifier is demonstrated to be the best. The experimental results showed that defects on optical devices could be detected efficiently by the proposed methods.

SIFT, LDF, cluster algorithm, image segmentation, image mosaic, dark-field imaging, optical devices