Title :
Comparison of different segmentation techniques in detection of flaws in weldments
Author :
Rathod, Vijay R. ; Anand, R.S. ; Alaknanda
Author_Institution :
Dept. of ElectricalEngineering, Indian Inst. of Technol. Roorkee, Roorkee, India
Abstract :
This paper presents Analysis and assessment of welding images and different techniques involved in detection of flaws in weldments, The efficient and reliable detection of defects is one of the important Task in Nondestructive testing (NDT) And Nondestructive evaluation (NDE) but before that concept of analysis of welded images and its classification is very important, Multiple methods are available for extraction of features. It has been widely known and also these methods serve as powerful tools for weldments. Image segmentation, Artificial neural network, Pattern recognition, Morphological processing, Using Bayesian networks and Advanced Neuro Fuzzy Techniques can be Analyzed and implemented as per the desired requirements in NDT and NDE.
Keywords :
belief networks; feature extraction; flaw detection; fuzzy set theory; image segmentation; neural nets; production engineering computing; welding; Bayesian networks; advanced neuro fuzzy techniques; artificial neural network; features extraction; flaws detection; image segmentation; morphological processing; nondestructive evaluation; nondestructive testing; pattern recognition; segmentation techniques; welding images; weldments; Artificial neural networks; Bayesian methods; Feature extraction; Fuzzy neural networks; Image analysis; Image segmentation; Nondestructive testing; Pattern analysis; Pattern recognition; Welding; Artificial neural network; Feature extraction; Image segmentation; Morphological processing; Using Bayesian networks And Advanced Neuro Fuzzy Techniques; Weldments;
Conference_Titel :
Computer and Automation Engineering (ICCAE), 2010 The 2nd International Conference on
Conference_Location :
Singapore
Print_ISBN :
978-1-4244-5585-0
Electronic_ISBN :
978-1-4244-5586-7
DOI :
10.1109/ICCAE.2010.5451722
