An effective IP algorithm for active IR thermographs: detecting defects metallic stuffs. (1st January 2011)

• Record Type: Journal Article
• Authors: Azad, D.; Rekha, H.S.; Ramji, K.
• Is Part Of: International journal of multimedia intelligence and security. Volume 2:Number 3/4(2011)
• Page Start: 296
• Page End: 319
• Publication Date: 2011-01-01
• Subjects: IR thermography image -- defects -- genetic algorithm -- colour segmentation -- HSV -- filtering and labelling; Security systems -- Periodicals; Data protection -- Periodicals; Computer security -- Periodicals; Biometric identification -- Periodicals; 005.8
• DOI: 10.1504/IJMIS.2011.044730
• Languages: English
• ISSNs: 2042-3462

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.