RETRACTED ARTICLE: Localization and segmentation of metal cracks using deep learning

Abstract

Detection and quantification of defects from metal and metal-coated surfaces is one of the main challenges in computer vision-based semantic segmentation. Manual inspection is not a practically feasible solution for identifying defects such as surface-level cracks, scratches, and manufacturing mistakes, especially when we have to deal with large number of test subjects. The metal defects can be of different size, shape, and texture and often show close resemblance to the possible artefacts due to normal wear and tear and brush markings of metal coating. Hence it will be quite challenging to come up with an efficient segmentation method for quantifying such defects. In this work, we propose an automatic segmentation and quantification approach for inspecting defects from digital images of titanium-coated metal surfaces with a customized Deep learning architecture: UNet. The scheme uses a supervised learning approach with convolutional neural network (CNN) and can learn the suitable representations and features from the training data without any handcrafted features or human intervention. The proposed image segmentation method also uses appropriate pre-processing and post-processing stages. The input images are filtered using median filter for eliminating possible impulse noises, and the output mask generated from the CNN model is post-processed using suitable morphological operations for eliminating false detections. The detection and segmentation performance is evaluated using standard benchmarks, and the overall Dice score of the proposed model is 91.67% with a precision of 93.46%.