Author/Authors :
SOO, SAY LEONG Universiti Sains Malaysia, Engineering Campus - School of Mechanical Engineering, Malaysia , MARAN RATNAM, MANI Universiti Sains Malaysia, Engineering Campus - School of Mechanical Engineering, Malaysia , SAMAD, ZAHURIN Universiti Sains Malaysia, Engineering Campus - School of Mechanical Engineering, Malaysia , KHALID, MOHD ASHHAR Malaysia Institute of Nuclear Technology Research (MINT) - Intelligent Systems Group, Malaysia
Abstract :
This paper presents a methodology to remove labels automatically from digitized weld radiographs as part of the automatic weld defect detection process. An algorithm was developed to detect and remove labels printed onto weld radiographs before weld extraction algorithm or defect detection algorithm is applied. Normality test was used to determine if the intensity profile parallel to the weld contains label pixels. Thresholding followed by region filling operations were carried out to remove the labels. The algorithm was tested on 50 weld radiographs with labels and the labels on 90% of these images were successfully removed
