Title :
Wall crack detection based on image processing
Author :
Hu, Dongna ; Tian, Tian ; Yang, Hengxiang ; Xu, Shibo ; Wang, Xiujin
Author_Institution :
Sch. of Comput. Sci. & Technol., Tianjin Univ., Tianjin, China
Abstract :
In this paper, a novel crack detection method is proposed based on the digital image of building external wall. We strive to record the wall surface condition accurately, and then get the linear characteristics of the image for crack recognition. This paper first does image edge detection, image binary of adaptive threshold and removal of isolated points, obtaining effective linear characteristics. Finally we distinguish the cracks and the normal lines through the curve fitting and its parameter analysis. The experimental results are satisfactory.
Keywords :
crack detection; curve fitting; edge detection; image segmentation; walls; adaptive threshold; crack recognition; curve fitting; digital image processing; image binary; image edge detection; isolated points removal; linear characteristics; parameter analysis; wall crack detection method; wall surface condition; Buildings; Correlation; Feature extraction; Fitting; Heuristic algorithms; Image edge detection; Image segmentation;
Conference_Titel :
Intelligent Control and Information Processing (ICICIP), 2012 Third International Conference on
Conference_Location :
Dalian
Print_ISBN :
978-1-4577-2144-1
DOI :
10.1109/ICICIP.2012.6391474
