Weld Extraction from Digitised Radiographs Using Graphical Analysis of Weld Intensity Profiles (original) (raw)
Related papers
Automatic Label Removal from Digitized Weld Radiographs
penerbit.utm.my
This paper presents a methodology to remove labels automatically from digitized weld radiographs as part of the automatic weld defect detection process. An algorithm was developed to detect and remove labels printed onto weld radiographs before weld extraction algorithm or defect detection algorithm is applied. Normality test was used to determine if the intensity profile parallel to the weld contains label pixels. Thresholding followed by region filling operations were carried out to remove the labels. The algorithm was tested on 50 weld radiographs with labels and the labels on 90% of these images were successfully removed.
Weld defect detection in industrial radiography based digital image processing
2005
Industrial radiography is a famous technique for the identification and evaluation of discontinuities, or defects, such as cracks, porosity and foreign inclusions found in welded joints. Although this technique has been well developed, improving both the inspection process and operating time, it does suffer from several drawbacks. The poor quality of radiographic images is due to the physical nature of radiography as well as small size of the defects and their poor orientation relatively to the size and thickness of the evaluated parts. Digital image processing techniques allow the interpretation of the image to be automated, avoiding the presence of human operators making the inspection system more reliable, reproducible and faster. This paper describes our attempt to develop and implement digital image processing algorithms for the purpose of automatic defect detection in radiographic images. Because of the complex nature of the considered images, and in order that the detected defect region represents the most accurately possible the real defect, the choice of global and local preprocessing and segmentation methods must be appropriated.
Image processing for radiographic films of weld inspection
cerc.wvu.edu
One of the professional domains in industry is weld inspection which deals with investigating the inside or outside (surface) of the weld to trace any defects which may cause failure in the system. Likewise, one of the methods of weld inspection is radiographic film interpretation (RI). In this method the specific weld will be captured in radiographic films and then an inspector will interpret them to identify any defects similar to the job that an orthopaedist does.
Automatic recognition of welding defects in real-time radiography
NDT International, 1990
This paper describes a real-time radiography configuration for the automatic inspection of welds. The optimal geometrical imaging configuration is evaluated and discussed in relation to conventional film radiography. For the automatic inspection of X-ray images, a two-step analysis was adopted: a fast search for defective regions, followed by fine identification and location of defects. Two different algorithms, based on the relative irregular behaviour of a defect, were develoPed for the fast search procedure. The second step, fine identification, can be achieved by a sequential similarity detection algorithm or by a thresholding algorithm. The different methods were applied to various X-ray images of welds and the automatic inspection was evaluated and compared with visual inspection.
Todays, the range of applications of image processing in various fields such as medical, robotics, agriculture and meteorology spread. Several studies have been conducted in these areas, but little researches have been done regarding its application in weld inspection. To test the groove and complete joint penetrating high-strength welding defects (such as pressure vessels, heat boilers, etc.) used radiography testing method. In the case of defects that are similar but have different acceptance criteria, minimize or eliminate the errors in radiography films by optimizing images using image processing. In image processing, edge detection, improving image quality and accurate color diagnosis is possible and help to accurately identifying of defects and decreases errors in diagnosis of defects type. In this study, the method for detection of internal defects of weld in radiography films using image processing will be investigated that its results can be used to eliminate the need for human interpretation of film and fully automate it using a machine.so first the general and basic concepts related to image processing, as well as a variety of weld defects will be described, then, using the results of research and development, effective way to identify defects using image processing algorithms will be provided and implement procedures and methods of it, using MATLAB software will be explained.
Statistical Tools for Weld Defect Evaluation in Radiographic Testing
… of 12th European conference on non- …, 2006
A reliable detection of defects in welded joints is one of the most important tasks in non-destructive testing by radiography, since the human factor still has a decisive influence on the evaluation of defects on the film. An incorrect classification may disapprove a piece in good conditions or approve a piece with discontinuities exceeding the limit established by the applicable standards. The progresses in computer science and the artificial intelligence techniques have allowed the welded joint quality interpretation to be carried out by using pattern recognition tools, making the system of the weld inspection more reliable, reproducible and faster. In this work, we develop and implement algorithms based on statistical approaches for segmentation and classification of the weld defects. Because of the complex nature of the considered images and so that the extracted defect area represents the most accurately possible the real defect, and that the detected defect corresponds as well as possible to its real class, the choice of the algorithms must be very judicious. In order to achieve this, a comparative study of the various segmentation and classification methods was performed to demonstrate the advantages of the ones in comparison with the others giving to the most optimal combinations.
Image Thresholding for Weld Defect Extraction in Industrial Radiographic Testing
International Journal of Signal …, 2006
In non destructive testing by radiography, a perfect knowledge of the weld defect shape is an essential step to appreciate the quality of the weld and make decision on its acceptability or rejection. Because of the complex nature of the considered images, and in order that the detected defect region represents the most accurately possible the real defect, the choice of thresholding methods must be done judiciously. In this paper, performance criteria are used to conduct a comparative study of thresholding methods based on gray level histogram, 2-D histogram and locally adaptive approach for weld defect extraction in radiographic images.
Welding Defect Detection by Segmentation of Radiographic Images
2009
Detection of defects in metallic pieces is an important application in the field of non-destructive testing (NDT), particularly in an industrial setting. These defects are mainly due to manufacturing errors or welding processes. In this article we will focus on this second category of defects using segmentation techniques applied to the welded joints. Segmentation is one of the most difficult tasks in image processing, particularly in the case of noisy or low contrast images such as radiographic images of welds. In segmenting this type of image, many researchers have used neural networks and fuzzy logic methods. The results are impressive, however the methods require a complex implementation and are time consuming. In this work, we propose a new method for segmenting digitized radiographic images which is based on histogram analysis, contrast enhancement and image thresholding. Computing time is optimized by using integral images to calculate the local thresholds. Although the metho...
Weld classification in radiographic images: data mining approach
2002
The need for non-destructive evaluation (NDE) technologies for maintenance of complex welded structures such as pressure vessels, load bearing structural members and power plants has long been recognized. This paper presents an application of data mining approach for weld data extracted from reported radiographic images. Data mining is the extraction of implicit, previously unknown and potentially useful information from data. In recent times, machinelearning models such, as neural networks are becoming standard tools for data mining of scientific data. This paper addresses various issues related to data mining and demonstrates their application. The study highlights the two major aspects of insight of data and prediction of the model for the problem domain.
Automatic Defect Detection and Counting In Radiographic Weldment Images
International Journal of Computer Applications, 2010
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. The performance of the proposed algorithm is found better than the existing defect detection algorithms.