Font Comparison System Based on Multiple Similarity Metrics

Abstract

: Digital fonts are widely used in various fields such as documents, webpages, movie subtitles, etc., thus, how to select the best font for the content is an important issue. For the same font, the similarity calculated using different metrics is different. In this paper, we propose a font comparison system that considers different similarities by sorting the similarity of each font. For measuring similarity, we use MSE, PSNR, SSIM, and HaarPSI for image quality assessment, as well as Euclidean distance and cosine similarity in t-SNE to reduce the number of dimensions. We evaluate how the correlation to the font order of each comparison method changes depending on the resolution of the image, the character type, and the comparison method.