Defect Detection Based on Segmentation of Thermographic Images of Frequency Modulated Thermal Wave Imaging

To improve the usefulness of the data, the raw images acquired during non-destructive testing should be processed by image processing techniques. In this paper, by Frequency Modulated Thermal Wave Imaging, we use the image fusion technique to boost the detection capability of defects in a GFRP sample with 25 squared Teflon inserts of different sizes positioned at various depths. In applications such as detection, image segmentation is useful where it is difficult to process the entire image at a time. In this paper, Adaptive Thresholding Image segmentation is used to classify the delamination in Thermographic Images of Infrared Non-Destructive Research on images captured at two different times. Image fusion is later applied to segmented images. Image fusion is used to merge two or more pictures of a different focus and to provide the best picture quality. Fusion is carried out using the Basic Averaging Method here. Using Relative Foreground Area error, the performance of the proposed method is quantitatively assessed. The region and shape of an object are important parameters in the case of Non-Destructive Evaluation. Such parameters are contrasted with current methods of segmentation.