Defect Detection Based on Segmentation of Thermographic Images of Frequency Modulated Thermal Wave Imaging
V. Phani Bhushan1, K.S. Sagar Reddy2, K. Murali3
1V. Phani Bhushan, Research Scholar, Shri Venkateshwara University, Gajraula, U.P., India.
2Dr. K.S. Sagar Reddy, Research Supervisor, Shri Venkateshwara University, Gajraula, U.P., India.
3Dr. K. Murali, Associate Professor, Department of E.C.E., N.E.C., A.P., India.
Manuscript received on February 13, 2021. | Revised Manuscript received on February 25, 2021. | Manuscript published on February 28, 2021. | PP: 210-216 | Volume-10 Issue-3, February 2021. | Retrieval Number: 100.1/ijeat.C22410210321 | DOI: 10.35940/ijeat.C2241.0210321
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. 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: 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.
Keywords: NDT, Adaptive Thresholding, Image Fusion, Quantitative Analysis.
Scope of the Article: Thermal Engineering