Automatic segmentation of radiographic images in industrial applications

• Autorzy: Baniukiewicz P.
• Języki publikacji: EN

Abstrakty

EN

A technology that utilizes penetrating rays is one of the oldest nondestructive testing methods. Nowadays, the process of radiogram analysis is performed by qualified human operators and automatic systems are still under development. In this work we present advanced algorithms for automatic segmentation of radiographic images of welded joints. The goal of segmentation of a radiogram is to change and simplify representation of the image into a form that is more meaningful and easier to analyse automatically. The radiogram is divided into parts containing the weld line, image quality indicators, lead characters, and possible defects. Then, each part is analysed separately by specialized algorithms within the framework of the Intelligent System for Radiogram Analysis.

Słowa kluczowe

EN

radiography; nondestructive testing; image processing

PL

radiografia; rozpoznawanie wad; przetwarzanie obrazów

• Wydawca: Polish Academy of Sciences, Committee on Electrical Engineering
• Czasopismo: Archives of Electrical Engineering
• Rocznik: 2011
• Tom: Vol. 60, nr 3
• Strony: 349--356
• Opis fizyczny: Bibliogr. 8 poz., rys., tab.

Twórcy

autor

Baniukiewicz P.

• Department of Electrical and Computer Engineering, West Pomeranian University of Technology, Szczecin,

Bibliografia

• [1] Cary, Howard B., Modern Welding Technology, Prentice Hall, ISBN: 0130309133 (2001).
• [2] European Commission sponsored project Development of novel digital radiography technology. To facilitate the traditionally less research intensive inspection industry sector change from manual film radiography to automated digital. Contract No NMP2-C-2005-515746.
• [3] http://www.technic-control.com.pl/
• [4] Sikora R., Baniukiewicz P., Chady T., et al. Comparison of selected weld defect extraction methods. Review of Progress in Quantitative Nondestructive Evaluation, AIP Conference Proceedings 975: 1034-1041 (2008).
• [5] European norm EN 462, part 1. Non-destructive testing – Image quality of radiographs – Part 1: Image quality indicators (wire type) – Determination of image quality value. (1994).
• [6] Mehmet Sezgin, Bülent Sankuj, Survey over image thresholding techniques and quantitative performance evaluation, Journal of Electronic Imaging 13(1): 146-165 (2004).
• [7] Jaakko Sauvola, Matti Pietikäinen, Adaptive document image binarization. Pattern Recognition 33: 225-236 (2000).
• [8] Derrode S., Ghorbel F., Robust and efficient Fourier-Mellin transform approximations for gray-level image reconstruction and complete invariant description. Computer Vision and Image Understanding 83(1): 57-78 (2001).