Abstract
This study presents an innovative approach to segmenting pores in low-quality industrial radiographic images using advanced image processing and adaptive segmentation techniques. The process involves several steps, including conversion of the image to grayscale to simplify analysis. Gaussian and median filters are then applied to improve image quality and enable more accurate segmentation. The methodology is based on adaptive thresholding and edge detection using the Canny algorithm, achieving accurate pore area measurements, even for those unnoticed by experts, with measurement errors of less than 0.1 mm². This high accuracy supports the method's effectiveness in pore detection and measurement. The resulting tool has great potential in industrial radiography applications, from quality control to defect analysis. While recognizing the need for continued research to improve contrast and illumination, as well as to address potential sources of error, these refinements promise to further elevate an already reliable and accurate method with a wide reach in the industry.

This publication has 22 references indexed in Scilit: