Abstract
Image processing and image analysis are the main aspects for obtaining information from digital image owing to the fact that this techniques give the desired details in most of the applications generally and Non-Destructive testing specifically. This paper presents a proposed method for the automatic detection of weld defects in radiographic images. Firstly, the radiographic images were enhanced using adaptive histogram equalization and are filtered using mean and wiener filters. Secondly, the welding area is selected from the radiography image. Thirdly, the Cepstral features are extracted from the Higher-Order Spectra (Bispectrum and Trispectrum). Finally, neural networks are used for feature matching. The proposed method is tested using 100 radiographic images in the presence of noise and image blurring. Results show that in spite of time consumption, the proposed method yields best results for the automatic detection of weld defects in radiography images when the features were extracted from the Trispectrum of the image.
Highlights
Non-Destructive Testing Non Destructive Testing (NDT) has been considered as a simple laboratory curiosity but throughout the past Five decades, it was proved to be one of the essential tools in industry
The results show that the contrast enhancement and the image filtering improve the radiographic image quality by improving the contrast between the image background and the weld defect regions
The results show that the detection rate is increase by increasing the Signal to Noise Ratio (SNR), and the parametric methods for higher order spectra estimation give higher detection rate than the nonparametric methods or Power Density Spectrum (PDS) estimated by Multiple Signal Classification (MUSIC) method
Summary
Non-Destructive Testing NDT has been considered as a simple laboratory curiosity but throughout the past Five decades, it was proved to be one of the essential tools in industry. Welding can be defined as the process of combining metals using heat, pressure or both with or without a filler metal to produce localized union through fusion or recrystallization across the interface [1] It is essentially used for several reasons such as the lack or the difficulty of a material to function solely, economic reasons, simplicity in usage as well as maintenance and repair. Non Destructive Testing (NDT) methods are used for welding process inspection by examining the surface and subsurface of the weld and surrounding base material. When less absorption occurs owing to a thin section of metal, dark regions appear in the radiograph, where more penetration of the rays takes place.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
