Welding defect detection from radiography images with a cepstral approach

Kasban, H.; Zahran, O.; Arafa, Hany; El-Kordy, M.; Elaraby, S. M.; El‐Samie, Fathi E. Abd

doi:10.1016/j.ndteint.2010.10.005

Cited by 65 publications

(30 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing literature contains a variety of these segmentation methods applied in the domain of NDT. Many of these methods are designed for a particular application, such as the detection of weld defects (Alaknanda et al, ; Vilar et al., ; Yazid et al., ; Kasban et al., ) or pipe deterioration (Peska, ; Liu et al., ), and/or for particular image sources, such as optical (Yazid et al., ), thermal (Abdel‐Qader et al., ; Liu et al., ; Yishuo and Jer‐Wei, ; Heriansyah and Abu‐Bakar, ), ultrasonic (Molero et al., ; D'Orazio et al., ), and radiography (Alaknanda et al, ; Vilar et al., ; Yazid et al., ; Kasban et al., ). As such, while these techniques may be effective for their designated purposes, they are understandably unlikely to perform well when applied to richly detailed, high‐resolution optical images of a broad range of surface types and damage forms in complex natural scenes.…”

Section: Introductionmentioning

confidence: 99%

Regionally Enhanced Multiphase Segmentation Technique for Damaged Surfaces

O’Byrne

Ghosh

Schoefs

et al. 2014

Computer aided Civil Eng

View full text Add to dashboard Cite

Imaging‐based damage detection techniques are increasingly being utilized alongside traditional visual inspection methods to provide owners/operators of infrastructure with an efficient source of quantitative information for ensuring their continued safe and economic operation. However, there exists scope for significant development of improved damage detection algorithms that can characterize features of interest in challenging scenes with credibility. This article presents a new regionally enhanced multiphase segmentation (REMPS) technique that is designed to detect a broad range of damage forms on the surface of civil infrastructure. The technique is successfully applied to a corroding infrastructure component in a harbour facility. REMPS integrates spatial and pixel relationships to identify, classify, and quantify the area of damaged regions to a high degree of accuracy. The image of interest is preprocessed through a contrast enhancement and color reduction scheme. Features in the image are then identified using a Sobel edge detector, followed by subsequent classification using a clustering‐based filtering technique. Finally, support vector machines are used to classify pixels which are locally supplemented onto damaged regions to improve their size and shape characteristics. The performance of REMPS in different color spaces is investigated for best detection on the basis of receiver operating characteristics curves. The superiority of REMPS over existing segmentation approaches is demonstrated, in particular when considering high dynamic range imagery. It is shown that REMPS easily extends beyond the application presented and may be considered an effective and versatile standalone segmentation technique.

show abstract

Section: Introductionmentioning

confidence: 99%

Regionally Enhanced Multiphase Segmentation Technique for Damaged Surfaces

O’Byrne

Ghosh

Schoefs

et al. 2014

Computer aided Civil Eng

View full text Add to dashboard Cite

show abstract

“…The image features are the most basic characteristics, it used to distinguish an image from others. The Mel Frequency Cepstral Coefficients (MFCCs) and the polynomial coefficients are used successfully in weld defect detection from radiographic images [12,13]. The Melscale is a mapping between the real frequency scale in Hz (f linear ) and the perceived frequency scale in Mels (f mel ).…”

Section: Feature Extractionmentioning

confidence: 99%

“…The Melscale is a mapping between the real frequency scale in Hz (f linear ) and the perceived frequency scale in Mels (f mel ). The Mapping is virtually linear below 1 kHz and logarithmic above as given by the following equation [12]:…”

Section: Feature Extractionmentioning

confidence: 99%

“…The automatic weld defect detection in radio- graphy images has been studied by several researchers using various techniques and approaches [4][5][6][7][8][9][10][11]. Recently, Kasban et al [12,13] used Cepstral approaches depending on extracting the features from the transform domains or from the power density related to the images. The rest of this paper is organized as follows.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Higher-Order Statistics for Automatic Weld Defect Detection

Saber¹,

Selim²

2013

JSEA

View full text Add to dashboard Cite

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.

show abstract

“…There are many approaches to deconvolution such as linear, nonlinear, Fourier methods [25][26][27], and flow model fitting [20,21,28]. Deconvolution by solving a linear equation set was chosen for this work because obtaining the RTD is approached without preconceptions of the profile shape, unlike parameter fitting of a flow model.…”

Section: Introductionmentioning

confidence: 99%

Characterization of Microchannel Hemodialyzers Using Residence Time Distribution Analysis

Coblyn¹,

Truszkowska²

2016

J Flow Chem

View full text Add to dashboard Cite

Microchannel-based hemodialysis has a potential to improve survival rates and quality of life for end-stage renal disease patients compared to conventional hemodialysis technology. Characterization of hydrodynamic behavior in microchannel geometries is necessary for improving flow uniformity, a critical challenge in realizing a commercial device. A test loop was developed for measuring the impulse response of a tracer dye injected into a dialyzer test article for the purpose of developing residence time distributions (RTD) to characterize lamina design. RTD variance tended to lower for designs that are more dominated, volume-wise, by the microchannel array versus the headers. RTD results also emphasize how defect issues can significantly impact a microchannel device via discrepancies between conceptual and operational devices. A multisegmented CFD model, developed for pairing with the impulse response test loop and dialyzer, showed good agreement between visual observation of the tracer in simulations and experiments, and the shape and peak of the output profiles.

show abstract

Welding defect detection from radiography images with a cepstral approach

Cited by 65 publications

References 16 publications

Regionally Enhanced Multiphase Segmentation Technique for Damaged Surfaces

Regionally Enhanced Multiphase Segmentation Technique for Damaged Surfaces

Higher-Order Statistics for Automatic Weld Defect Detection

Characterization of Microchannel Hemodialyzers Using Residence Time Distribution Analysis

Contact Info

Product

Resources

About