Title :
Algorithm Study on Thinning and Keeping Connectivity of Bituminous Pavement Crack Images
Author_Institution :
Correspondence Eng. Dept., Eng. Coll. of CAPF, Xi´´an, China
Abstract :
The main research point is the thinning method to the pavement crack images through using mathematical morphology in this paper. The efficient steps of the thinning algorithm are given for binary images and the satisfactory thinned images are obtained through experiments. In some cases, the thinned images will produce cavities or breakpoints, it needs to be processed by closing method in order to keep the connctivity of the thinned images. Experimental result shows improvement in both operational speed and accuracy rate, and it is satisfatory. Expected to be applied to the automatic detection of road surface defects, for the highway management and maintenance department to provide scientific basis for decision-making.
Keywords :
crack detection; decision making; feature extraction; mathematical morphology; roads; structural engineering computing; automatic detection; binary image; bituminous pavement crack image; decision making; highway management; maintenance department; mathematical morphology; operational speed; thinning method; Diseases; Feature extraction; Maintenance engineering; Morphology; Noise; Pixel; Skeleton; closing; connectivity; crack image; skeleton; thinning;
Conference_Titel :
Information Science and Management Engineering (ISME), 2010 International Conference of
Conference_Location :
Xi´an
Print_ISBN :
978-1-4244-7669-5
Electronic_ISBN :
978-1-4244-7670-1
DOI :
10.1109/ISME.2010.265