Abstract
A more effective and accurate improved Sobel algorithm has been developed to detect surface defects on heavy rails. The proposed method can make up for the mere sensitivity to X and Y directions of the Sobel algorithm by adding six templates at different directions. Meanwhile, an experimental platform for detecting surface defects consisting of the bed-jig, image-forming system with CCD cameras and light sources, parallel computer system and cable system has been constructed. The detection results of the backfin defects show that the improved Sobel algorithm can achieve an accurate and efficient positioning with decreasing interference noises to the defect edge. It can also extract more precise features and characteristic parameters of the backfin defect. Furthermore, the BP neural network adopted for defects classification with the inputting characteristic parameters of improved Sobel algorithm can obtain the optimal training precision of 0.0095827 with 106 iterative steps and time of 3 s less than Sobel algorithm with 146 steps and 5 s. Finally, an enhanced identification rate of 10% for the defects is also confirmed after the Sobel algorithm is improved.
Similar content being viewed by others
References
ZHENG Ran, LIU Ze, LU Ying-fei, ZHU Li-xiong, SUN **u-fang. Multi-frequency least squares demodulation method in electromagnetic rail inspection [C]//IEEE International Conference on Imaging Systems and Techniques. New York: IEEE Press, 2013, 363–365.
MUNOZ J M C, MARQUEZ F P G, PAPAELIAS M. Railroad inspection based on ACFM employing a non-uniform B-spline approach [J]. Mechanical Systems and Signal Processing, 2013, 40(2): 605–617.
MI Zeng-zhen, XIE Zhi-jiang. Theoretical and experimental research on the defects of hot rolled heavy rail [J]. Metalurgia International, 2012, 17(9): 221–225.
KHODAYARI-ROSTAMABAD A, REILLY J P, NIKOLOVA N K, HARE J R, PASHA S. Machine learning techniques for the analysis of magnetic flux leakage images in pipeline inspection [J]. IEEE Transaction on Magnetic, 2009, 45(8): 3073–3084.
LEI Hua-ming, TIAN Gui-yun. Broken wire detection in coated steel belts using the magnetic flux leakage method [J]. Insight, 2013, 55(3): 126–131.
RAMOS H G, ROCHA T, KRAL J, PASADAS D, RIBEIRO A L. An SVM approach with electromagnetic methods to assess metal plate thickness [J]. Measurement, 2014, 54: 201–206.
KHALID A R, PAILY R. FPGA implementation of high speed and low power architectures for image segmentation using Sobel operators [J]. Journal of Circuits Systems and Computers, 2012, 21(7): 1250050.1-1250050.14.
CAI Jian-hua, HU Wei-wen. Feature extraction of gear fault signal based on Sobel operator and WHT [J]. Shock and Vibration, 2013, 20(3): 551–559.
ABBASI T A, ABBASI M U. A novel FPGA-based architecture for Sobel edge detection operator [J]. Internatinal Journal of Electronics, 2007, 94(9): 889–896.
WANG Zu-**, HUANG **ao-diao. Visual positioning of rectangular lead components based on Harris corners and Zernike moments [J]. Journal of Central South University, 2015, 22(7): 2586–2595.
ZHANG Qi, YANG Hao, WEI Yu-guang. Selection of destination ports of inland-port-transferring RHCTS based on sea-rail combined container transportation [C]//3rd International Symposium on Innovation and Sustainability of Modern Railway. Bei**g: Science Press, 2012, 675–680.
CAO Su-qun, CHEN Wei-min, Zhang Hong. An integration method for edge detection [J]. Advanced Electrical and Electronics Engineering, 2011, 2: 243–249.
ZHANG Hu, ZHU Qiu-**, FAN Ci-en, DENG De-xiang. Image quality assessment based on Prewitt magnitude [J]. AEU-International Journal of Electronics and Communications, 2013, 67(9): 799–803.
PANDEY M. Different operator using in edge detection for image processing [J]. International Journal of Computer Science Engineering and Information Technology Research, 2014, 4(1): 57–61.
MEDINA-CARNICER R, MUNOZ-SALINAS R, YEGUASBOLIVAR E, DIAZ-MAS L. A novel method to look for the hysteresis thresholds for the Canny edge detector [J]. Pattern Recognition, 2011, 44(6): 1201–1211.
PANETTA K A, AGAIAN S S, NERCESSIAN S C, ALMUNSTASHRI A A. Shape-dependent canny edge detector [J]. Optical Engineering, 2011, 50(8): 087008.
JIA **ao-fen, ZHAO Bai-ting, ZHOU Meng-ran, CHEN Zhao-quan. An edge-adaptive demosaicking method based on image correlation [J]. Journal of Central South University, 2015, 22(4): 1397–1404.
GUO Yan-wen. Adaptive preprocessing algorithms of corneal topography in polar coordinate system [J]. Journal of Central South University, 2014, 21(12): 4571–4576.
MARTINI M G, HEWAGE C, VILLARINI B. Image quality assessment based on edge preservation [J]. Signal Processing-Image Communication, 2012, 27(8): 875–882.
ZHAO Ji-yin, XU Yan-lei, JIAO Yu-bin. The fast arithmetic study of image edge detection based on the order morphology [J]. Acta Electronica Sinica, 2008, 36(11): 2195–2199. (in Chinese)
ZHAO Zhi-gang, WAN Jiao-na. New method for image edge detection based on gradient and zero crossing [J]. Chinese Journal of Scientific Instrument, 2006, 27(8): 821–824. (in Chinese)
ZHENG Ying-juan, ZHANG You-hui, WANG Zhi-wei, ZHANG Jiang, FAN Sheng-juan. Edge detection algorithm based on the eight directions sobel operator [J]. Computer Science A, 2013, 40(11): 354–356. (in Chinese)
LIU Yuan-jiong. Research on imaging optimization and depth information extraction of steel plate surface defects based on image processing [D]. Wuhan: Wuhan University of Science and Technology, 2011. (in Chinese)
WANG Wen-yuan. Selecting the optimal gaussian filtering scale via the SNR of image [J]. Journal of Electronics & Information Technology, 2009, 31(10): 2483–2487. (in Chinese)
Author information
Authors and Affiliations
Corresponding author
Additional information
Foundation item: Project(51174151) supported by the National Natural Science Foundation of China; Project(2010Z19003) supported by the Major Scientific Research Program of Hubei Provincial Department of Education, China; Project(2010CDB03403) supported by the Natural Science Foundation of Science and Technology Department of Hubei Province, China
Rights and permissions
About this article
Cite this article
Shi, T., Kong, Jy., Wang, Xd. et al. Improved Sobel algorithm for defect detection of rail surfaces with enhanced efficiency and accuracy. J. Cent. South Univ. 23, 2867–2875 (2016). https://doi.org/10.1007/s11771-016-3350-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11771-016-3350-3