سال انتشار: ۱۳۸۹

محل انتشار: ششمین کنفرانس ماشین بینایی و پردازش تصویر

تعداد صفحات: ۵

نویسنده(ها):

M. Ziashahabi – Department of Electrical Engineering, Shahed University, Tehran, Iran
H. Sadjedi – Department of Electrical Engineering, Shahed University, Tehran, Iran
H Khezripour – Department of Computer Engineering , Amir-Kabir Univ, Tehran

چکیده:

Defects on the Pipeline surface such as cracks cause main problems for governments, specifically when the pipeline is covered under the ground. Manual examination for surface defects in the pipeline has several disadvantages, including varying standards, and high cost. In this paper, a combination of two algorithms based on mathematical morphology and curvature evaluation for segmentation of defects is proposed. Then, we use fuzzy k-means clustering to classify pipe defects. The proposed method can be completely automated and has been tested on more than 250 scanned images of petroleum pipelines of Iran