Nondestructive inspection of aerospace composite laminate using thermal image processing

In this work, a novel image segmentation method in thermographic images using the computer vision algorithm, active contours, is presented. These studies were done on thermal images obtained from pulse thermography. Many aerospace components are made of composite laminates. De-bonds/de-laminations set in during the manufacturing or in-service stages of these materials. Identification of de-bonds in composite laminates is a difficult task and faces many challenges when it is done through the processing of thermographic images. The first challenge is to get an accurate seed point to be used in active contours. In this study, the seed points for active contours were obtained from the moving averages of the pixel values taken along the region of interest lines. It is shown that the active contours with the help of seed points identified through this method are able to distinguish the de-bonds. The experimental results, supported by segmentation metrics, suggest that the segmentation method used here outperforms some earlier results which were based on the combination of Gabor filters, watershed models and divide-and-conquer methods such as subdivision of images.