An effective IP algorithm for active IR thermographs: detecting defects metallic stuffs
by D. Azad; H.S. Rekha; K. Ramji
International Journal of Multimedia Intelligence and Security (IJMIS), Vol. 2, No. 3/4, 2011

Abstract: In metal objects, identifying defects using thermography image and fixing the defective area in the original image are two most important processes. Though many researches have been proposed for the identification of cracks or holes in the system, and marked only in the thermography image, but not in the original image. By overcoming these drawbacks, here a new technique to identify the defective region in the thermography image and for locating the defective part in the original image was proposed. For identification of defective part in the thermography image colour segmentation process is used and genetic algorithm is used for fixing the defective region in the original image. This enables easy identification of the affected part in the system. The proposed methodology is compared with PSO technique and the method is simulated and tested using different thermographs. Then the performance of the system is analysed using the obtained results. The obtained results show that our technique accurately identifies the cracks or holes in the system and fixes the defective part in the original image.

Online publication date: Sat, 28-Feb-2015

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Multimedia Intelligence and Security (IJMIS):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com