Multiclass defect detection and classification in weld radiographic images using geometric and texture features

Authors:
Ioannis Valavanis;Dimitrios Kosmopoulos
Affiliations:
Zenon Automation Technologies, 15354 Glyka Nera, Greece;Computational Intelligence Laboratory, Institute of Informatics and Telecommunications, National Center for Scientific Research "Demokritos", 15310 Aghia Paraskevi, Greece
Venue:
Expert Systems with Applications: An International Journal
Year:
2010

Citing 5
Cited 3

Feature Selection: Evaluation, Application, and Small Sample Performance

IEEE Transactions on Pattern Analysis and Machine Intelligence
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
On the algorithmic implementation of multiclass kernel-based vector machines

The Journal of Machine Learning Research
Efficient Graph-Based Image Segmentation

International Journal of Computer Vision
Classification of weld flaws with imbalanced class data

Expert Systems with Applications: An International Journal

NDE weld defect detection and feature extraction using segmentation approach

International Journal of Advanced Intelligence Paradigms
Computer techniques towards the automatic characterization of graphite particles in metallographic images of industrial materials

Expert Systems with Applications: An International Journal
Statistical detection of defects in radiographic images using an adaptive parametric model

Signal Processing

Quantified Score

Hi-index	12.05

Visualization

Abstract

In this paper, a method for the detection and classification of defects in weld radiographs is presented. The method has been applied for detecting and discriminating discontinuities in the weld images that may correspond to false alarms or defects such as worm holes, porosity, linear slag inclusion, gas pores, lack of fusion or crack. A set of 43 descriptors corresponding to texture measurements and geometrical features is extracted for each segmented object and given as input to a classifier. The classifier is trained to classify each of the objects it into one of the defect classes or characterize it as non-defect. Three fold cross validation was utilized and experimental results are reported for three different classifiers (Support Vector Machine, Neural Network, k-NN).