Comparing Handwriting Fluency in English Language Teaching Using Computer Vision Techniques.

Educational materials play a vital role in effectively conveying information to learners, with the readability and legibility of written text serving as crucial factors. This study investigates the influence of font selection on educational materials and explores the relationship between handwriting fluency and cognitive load. By identifying challenges in written expression, such as reduced working memory capacity, text organization difficulties, and content recall issues, the study sheds light on the significance of neat handwriting. The research emphasizes the relevance of neat handwriting in critical examinations, including college entrance exams, academic English exams, and job interviews, where the fluency of one’s handwriting can impact the decision-making process of interviewers. This highlights the value of handwriting fluency beyond educational contexts. Advancements in computer science and machine vision present new opportunities for automating font evaluation and selection. By employing machine vision algorithms to objectively analyze visual features of fonts, such as serifs, stroke width, and character spacing, the legibility and readability of fonts used in English language teaching materials are assessed. In this study, machine vision techniques are applied to score fonts used in educational materials. The OpenCV computer vision library is utilized to extract visual features of fonts from images, enabling the analysis of their legibility and readability. The primary objective is to provide educators with an automated and objective tool for scoring handwriting, reducing visual fatigue, and ensuring impartial evaluations. This research contributes to enhancing the quality of educational materials and provides valuable insights for educators, researchers, and font designers.