Algorithm Study of Edge Location and Feature Measurement of Building Surface Crack Images

Abstract:

Old buildings surface cracks are more obvious with the accumulation of its disrepair, which will impact aesthetics, durability and even threaten the safety of persons and properties if feature values surpass the security thresholds. In this paper, firstly, the algorithm of the improved Canny operator gray threshold edge detection and location, based on traditional differential operators and sub-pixel positioning algorithms, achieve coarse location, furthermore, the sub-pixel location algorithm of Gaussian curve fitting based on neighbor gradient features realize sub-pixel precision positioning. Finally, crack features are calculated and comparative analysis through the measurement algorithm. The experiments prove the algorithms possess high accuracy and feasibility with important application values of assessment, identification and maintenance.

• Periodical: Applied Mechanics and Materials (Volumes 380-384)
• Pages: 1045-1049
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.380-384.1045
• Online since: August 2013
• Authors: Lei Cui, Qing Zhu, Jing Kang Zhang
• Keywords: Crack Feature Measurement, Curve Fitting, Differential Operators, Edge Detection-Extraction, Sub-Pixel Positioning

References

[1] WU Sheng-xing, ZHAO Guo-fan. Finite element method of crack width computation in concrete structure[J]. CHINESE JOURNAL OF COMPUTATIONAL MECHANICS. 1997(1).

[2] WANG Jing, LI Hong-qi, XING Dong-mei, etc. Application of Digital Image Correlation Method in Bridge Cracks Measurement[J]. CHINESE QUARTERLY OF MECHANICS. 2003(4).

[3] GENG Fei, QIAN Chun-xiang. Image analysis technique for quantitative testing and evaluation of plastic shrinkage cracks in concrete[J]. Journal of Southeast University. 2003(6).

[4] Gonzalez R C, Woods R E. Digital Image Processing, Third Edition [M]. Beijing: Electronic Industry PRESS, 2011. 6.

[5] Canny J. A Computational Approach to Edge Detection[J]. IEEE Trans on Pattern Analysis and Machine Intelligence. 1986, 8(1): 679-697.

DOI: 10.1109/tpami.1986.4767851

[6] SHANG Ya-ceng, CHEN Jing, Tian Jun-wei. Sub-pixel edge detection algorithm based on Gauss fitting[J], Journal of Computer Application. 2011, 1, Vol. 31 No. 1.

DOI: 10.3724/sp.j.1087.2011.00179

[7] ANGELA C. Hyperbolic tangent algorithm for periodic effect cancellation in sub-pixel resolution edge displacement measurement[J]. Measurement, 2009, 42(4): 1226-1232.

DOI: 10.1016/j.measurement.2009.06.001

[8] COLEMAN S A, SCONTNEY B W, HERRON M G. A validated edge model technique for the empirical performance evaluation of discrete zero-crossing methods[J]. Image and Vision Computing 2007, 25(6): 1315-1328.

DOI: 10.1016/j.imavis.2006.08.004

[9] YAO Bing, ZHAO Qi-lin, RUI Ting, etc. The Ranging Method of Concrete Bridge Cracks of No-contact Detection [J], CHINA MUNICIPAL ENGINEERING, 2009, 6(3): 38-40.

[10] HU Chang-hua, LI Guo-hua, LIU Tao, etc. System analysis and design based on MATLAB 6. x [M]. Xi'an: xidian university press, (2004).