Development of Automatic Crack Identification Algorithm for a Concrete Sleeper Using Pattern Recognition

패턴인식을 이용한 콘크리트침목의 자동균열검출 알고리즘 개발

  • Kim, Minseu (Institute of Railroad Convergence Technology, Korea National University of Transportation) ;
  • Kim, Kyungho (A BEST Co. Ltd.) ;
  • Choi, Sanghyun (Department of Railroad Facility Engineering, Korea National University of Transportation)
  • Received : 2017.02.10
  • Accepted : 2017.05.25
  • Published : 2017.06.30


Concrete sleepers, installed on majority of railroad track in this nation can, if not maintained properly, threaten the safety of running trains. In this paper, an algorithm for automatically identifying cracks in a sleeper image, taken by high-resolution camera, is developed based on Adaboost, known as the strongest adaptive algorithm and most actively utilized algorithm of current days. The developed algorithm is trained using crack characteristics drawn from the analysis results of crack and non-crack images of field-installed sleepers. The applicability of the developed algorithm is verified using 48 images utilized in the training process and 11 images not used in the process. The verification results show that cracks in all the sleeper images can be successfully identified with an identification rate greater than 90%, and that the developed automatic crack identification algorithm therefore has sufficient applicability.


Grant : 고해상도 카메라를 이용한 콘크리트 침목균열자동검출 시스템

Supported by : 중소기업청, 한국교통대학교


  1. M.S. Kaseko, Z. Lo, S. Ritchie (1994) Comparison of traditional and neural classifiers for pavement-crack detection, Journal of Transportation Engineering, 120(4), pp. 552-569.
  2. Y. Wang (1998) Neural network approach to image reconstruction from projections, International Journal of Imaging Systems and Technology, 9(5), pp. 381-387.<381::AID-IMA8>3.0.CO;2-6
  3. W. Benning, J. Lange, R. Schwermann, C. Effkemann, S. Gortz (2004) Monitoring crack origin and evolution at concrete elements using photogrammetry, International Archives of Photogrammetry Remote Sensing and Spatial Information Sciences, 35(5), pp. 678-683.
  4. I. Giakoumis, N. Nikolaidis, I. Pitas (2006) Digital image processing techniques for the detection and removal of cracks in digitized paintings, IEEE Transactions on Image Processing, 15(1), pp. 178-188.
  5. J. Ando, T. Nagao (2009) Automatic construction of accurate image processing using Adaboost, Fifth International Workshop on Computational Intelligence and Applications, Hiroshima University, Japan, pp. 296-301.
  6. A. Marques (2012) Automatic Road Pavement Crack Detection Using SVM, Thesis, Instituto Superior Tecnico, Lisbon, Portugal.
  7. B. Lee (2003) Development of Detecting System for Concrete Surface Cracks Using Image Processing and Artificial Neural Network, Thesis, Korea Advanced Institute of Science and Technology.
  8. B. Lee, J. Shin, C. Park (2008) Development of image processing program to inspect concrete bridges, Proceedings of 2008 Spring Annual Conference, Korea Concrete Institute, Yong Pyong, Korea, 20(1), pp. 189-192.
  9. C.-H. Choo, S.-W. Park, H.-T. Kim, K.-H. Jee, T.-G. Yoon (2011) Analysis and cause of occurrence of lining cracks on NATM tunnel based on the precise inspection for safety and diagnosis - Part I, Journal of Tunnelling and Undergraound Space Association, 13(3), pp. 199-214.
  10. Y. Freund, R.E. Schapire (1999) A short introduction to boosting, Journal of Japanese Society for Artificial Intelligence, 14(5), pp. 771-780.
  11. H. Han (2009) Introduction to Pattern Recognition, Hanbit Media, Seoul, Korea, pp. 514-523.
  12. R. Schapire, Y. Singer (1999) Improved boosting algorithms using confidence-rated predictions, Machine Learning, 37(3), pp. 297-335.
  13. K. Lee (2008) An Implementation for the Face Recognition Visual Monitoring System Using Adaboost and PCA Algorithm, Thesis, Ajou University.