Automatic Defect Detection and Counting In Radiographic Weldment Images
Digital Image Analysis is one of the most challenging and important tasks in many scientific and engineering applications. Extracting the Region Of Interest (ROI) from the image and recognition in image processing are very important steps. When these tasks are manually performed, it is tedious and difficult involving human experts. This paper focuses on automatic defect detection and counting in radiographic weldment images thus considering defects in weldment images as object of interest. To detect defects in radiographic weldment images, thresholding and segmentation algorithm is used and a new procedure is introduced for counting number of defects in the input images. The results obtained from the proposed work are impressive with respect to the computational time and defect detection rate.