Academic Journals Database
Disseminating quality controlled scientific knowledge

GROWING SELF ORGANIZED MAPS FOR RADIOGRAPHIC NON DESTRUCTIVE TESTING OF METALLIC PRODUCTS

ADD TO MY LIST
 
Author(s): Sarin CR | Manu R Krishnan

Journal: International Journal of Soft Computing & Engineering
ISSN 2231-2307

Volume: 1;
Issue: 6;
Start page: 311;
Date: 2012;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Automatic Quality Inspection | GSOM | NDT | Object detection

ABSTRACT
Manual inspection of metallic products can only be atime-consuming and is less reliable to find microscopic andinternal defects, therefore is an expensive task; it can also sufferfrom operator performance. The proposed system apply imageprocessing techniques to automatically inspect radiographicimages and evaluate the data to find faults and is based onImproved Growing Self organized Maps Segmentation. Thenumber of false detections is still high and will be addressed infuture research. Monitoring the defect or damage at an early stageis a very important as it allows to implement operations to classifyand correct defects and improves the safety, reliability, accuracy,and high throughput of the structure. This paper presents animproved intelligent methodology for Radiographic automatedvisual quality inspection and, which provides many advantagesover traditional methods. The accuracy of conventional systems isvery much depending on the selected features, which are extractedfrom defect images. Growing Self Organized Maps forRadiographic Non Destructive Testing is an advanced methodsuitable for crack detection, which gives a smoothed image toobtain uniform brightness, followed by removing isolated points toremove noise and morphological operations with fast operation.
Save time & money - Smart Internet Solutions      Why do you need a reservation system?