Answers are grounded in this paper and cite their sources.
Metal parts can get scratches, cracks and other defects on their surface. These defects spoil the quality and reduce the life of the part. Checking them by eye is slow and tiring, and two people may give two different answers. In this paper we plan a simple machine vision system that finds and sorts surface defects using digital image processing. The system takes an image, converts it to grayscale, removes noise, improves contrast, separates the defect area, cleans it with morphology, measures some features and then decides the defect type. We plan to test it on the NEU surface defect database, which has 1,800 images of six steel defect types. We want to keep the method light and low-cost, so it does not need a heavy deep-learning model. Accuracy, precision, recall, F1score and a confusion matrix will be used to check the performance. Experimental results are not included yet and will be added after the experiments are done.
No takes yet. Share an insight, caveat, or question.
Sarthak Erande (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: