Similarity Measurement of Symbols on Embossed Surfaces

At present, in the age of Industry 4.0, digital technology has been applying for automated quality control. This paper presents visual inspection on product surface embossed with industrial symbols. Image processing-based measurements of similarity of the symbol images were proposed. Peak signal-to-noise ratio (PSNR), the structural similarity index measure (SSIM), and correlation coefficient were evaluated and compared. The experimental results show that the proposed similarity indexes are efficiently enough to identify the symbols on embossed surfaces.