This paper mainly proposes a line segment detection method based on pseudo peak suppression and local Hough transform, which has good noise resistance and can solve the problems of short line segment missing detection, false detection, and oversegmentation. In addition, in response to the phenomenon of uneven development in nuclear emulsion tomographic images, this paper proposes an image preprocessing process that uses the “Difference of Gaussian” method to reduce noise and then uses the standard deviation of the gray value of each pixel to bundle and unify the gray value of each pixel, which can robustly obtain the linear features in these images. The tests on the actual dataset of nuclear emulsion tomographic images and the public YorkUrban dataset show that the proposed method can effectively improve the accuracy of convolutional neural network or vision in transformer-based event classification for alpha-decay events in nuclear emulsion. In particular, the line segment detection method in the proposed method achieves optimal results in both accuracy and processing speed, which also has strong generalization ability in high quality natural images.
Ye TIAN
Zhuzhou CRRC Times Electric Co., Ltd.
Mei HAN
Hunan University of Technology
Jinyi ZHANG
Shenyang Ligong University
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.
Copy
Ye TIAN, Mei HAN, Jinyi ZHANG, "Line Segment Detection Based on False Peak Suppression and Local Hough Transform and Application to Nuclear Emulsion" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 11, pp. 1854-1867, November 2023, doi: 10.1587/transinf.2023EDP7117.
Abstract: This paper mainly proposes a line segment detection method based on pseudo peak suppression and local Hough transform, which has good noise resistance and can solve the problems of short line segment missing detection, false detection, and oversegmentation. In addition, in response to the phenomenon of uneven development in nuclear emulsion tomographic images, this paper proposes an image preprocessing process that uses the “Difference of Gaussian” method to reduce noise and then uses the standard deviation of the gray value of each pixel to bundle and unify the gray value of each pixel, which can robustly obtain the linear features in these images. The tests on the actual dataset of nuclear emulsion tomographic images and the public YorkUrban dataset show that the proposed method can effectively improve the accuracy of convolutional neural network or vision in transformer-based event classification for alpha-decay events in nuclear emulsion. In particular, the line segment detection method in the proposed method achieves optimal results in both accuracy and processing speed, which also has strong generalization ability in high quality natural images.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2023EDP7117/_p
Copy
@ARTICLE{e106-d_11_1854,
author={Ye TIAN, Mei HAN, Jinyi ZHANG, },
journal={IEICE TRANSACTIONS on Information},
title={Line Segment Detection Based on False Peak Suppression and Local Hough Transform and Application to Nuclear Emulsion},
year={2023},
volume={E106-D},
number={11},
pages={1854-1867},
abstract={This paper mainly proposes a line segment detection method based on pseudo peak suppression and local Hough transform, which has good noise resistance and can solve the problems of short line segment missing detection, false detection, and oversegmentation. In addition, in response to the phenomenon of uneven development in nuclear emulsion tomographic images, this paper proposes an image preprocessing process that uses the “Difference of Gaussian” method to reduce noise and then uses the standard deviation of the gray value of each pixel to bundle and unify the gray value of each pixel, which can robustly obtain the linear features in these images. The tests on the actual dataset of nuclear emulsion tomographic images and the public YorkUrban dataset show that the proposed method can effectively improve the accuracy of convolutional neural network or vision in transformer-based event classification for alpha-decay events in nuclear emulsion. In particular, the line segment detection method in the proposed method achieves optimal results in both accuracy and processing speed, which also has strong generalization ability in high quality natural images.},
keywords={},
doi={10.1587/transinf.2023EDP7117},
ISSN={1745-1361},
month={November},}
Copy
TY - JOUR
TI - Line Segment Detection Based on False Peak Suppression and Local Hough Transform and Application to Nuclear Emulsion
T2 - IEICE TRANSACTIONS on Information
SP - 1854
EP - 1867
AU - Ye TIAN
AU - Mei HAN
AU - Jinyi ZHANG
PY - 2023
DO - 10.1587/transinf.2023EDP7117
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2023
AB - This paper mainly proposes a line segment detection method based on pseudo peak suppression and local Hough transform, which has good noise resistance and can solve the problems of short line segment missing detection, false detection, and oversegmentation. In addition, in response to the phenomenon of uneven development in nuclear emulsion tomographic images, this paper proposes an image preprocessing process that uses the “Difference of Gaussian” method to reduce noise and then uses the standard deviation of the gray value of each pixel to bundle and unify the gray value of each pixel, which can robustly obtain the linear features in these images. The tests on the actual dataset of nuclear emulsion tomographic images and the public YorkUrban dataset show that the proposed method can effectively improve the accuracy of convolutional neural network or vision in transformer-based event classification for alpha-decay events in nuclear emulsion. In particular, the line segment detection method in the proposed method achieves optimal results in both accuracy and processing speed, which also has strong generalization ability in high quality natural images.
ER -