Title :
A crack recognition way thru images for natural gas pipelines
Author :
Qingxin, Ding ; Fei, Tian ; Li, Xiaochun ; Yang, Zhaofeng
Author_Institution :
Faculty of Mechanical and Electronic Engineering, China University of Petroleum (Beijing) 102249, China
Abstract :
An algorithm for recognizing cracks through images is presented for detection of any crack in inner wall of long-distance natural gas pipeline under complicated environment. This algorithm has low requirement on the image quality, simple pre-processing procedure, takes single continuous image areas as individual part, and carries out fuzzy judgment on cracks by multiple threshold values and crack approaching factors. Experiments showed that the algorithm is simple, of high recognition efficiency and accurate judgment.
Keywords :
Algorithm design and analysis; Filtering; Gray-scale; Image edge detection; Pipelines; Pixel; Algorithm; Crack recognition; Image recognition;
Conference_Titel :
Information Science and Engineering (ICISE), 2010 2nd International Conference on
Conference_Location :
Hangzhou, China
Print_ISBN :
978-1-4244-7616-9
DOI :
10.1109/ICISE.2010.5690740
