Automatic Inspection of Potential Flaws In Glass Based on Image Segmentation

Glass defects which result into poor quality are a major reason of embarrassment for manufacturers. Glass defects are typically unavoidable, but their occurrence must be minimized during the production of highquality glasses. It is a tedious process to manually inspect very large size glasses. The manual inspection process is slow, time-consuming and prone to human error. Automatic inspection systems using image processing can overcome many of these disadvantages and offer manufacturers an opportunity to significantly improve the product quality and reduce costs. Common defects produced by these manufacturing techniques are scratches and cracks which are the real issue for the glass industry. Potential defects removal includes image denoising and FCM. Based upon the PSNR value comparison wiener filter is having highest PSNR value. Then the Universal Image Quality Index shows the segmentation parameters and Pearson correlation coefficient shows the amount of correlation.