Growing Self Organized Maps for Radiographic Non Destructive Testing of Metallic Products
Sarin CR1, Manu R Krishnan2
1Sarin CR, ME Mechatronics, Karpagam College of Engineering, Coimbatore –TN, India.
2Manu R Krishnan ME Mechatronics, Karpagam College of Engineering, Coimbatore –TN, India.
Manuscript received on December 07, 2011. | Revised Manuscript received on December 23, 2011. | Manuscript published on January 05, 2012. | PP: 311-317 | Volume-1 Issue-6, January 2012. | Retrieval Number: F0334121611/2012©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Manual inspection of metallic products can only be a time-consuming and is less reliable to find microscopic and internal defects, therefore is an expensive task; it can also suffer from operator performance. The proposed system apply image processing techniques to automatically inspect radiographic images and evaluate the data to find faults and is based on Improved Growing Self organized Maps Segmentation. The number of false detections is still high and will be addressed in future research. Monitoring the defect or damage at an early stage is a very important as it allows to implement operations to classify and correct defects and improves the safety, reliability, accuracy, and high throughput of the structure. This paper presents an improved intelligent methodology for Radiographic automated visual quality inspection and, which provides many advantages over traditional methods. The accuracy of conventional systems is very much depending on the selected features, which are extracted from defect images. Growing Self Organized Maps for Radiographic Non Destructive Testing is an advanced method suitable for crack detection, which gives a smoothed image to obtain uniform brightness, followed by removing isolated points to remove noise and morphological operations with fast operation.
Keywords: Automatic Quality Inspection, GSOM, NDT, Object detection.