Towards Visuo-Structural Handwriting Evaluation Based on Graph Matching.
International Conference of the International Graphonomics Society(2023)
摘要
Judging the quality of handwriting based on visuo-structural criteria is fundamental for teachers when accompanying children who are learning to write. Automatic methods for quality assessment can support teachers when dealing with a large number of handwritings, in order to identify children who are having difficulties. In this paper, we investigate the potential of graph-based handwriting representation and graph matching to capture visuo-structural features and determine the legibility of cursive handwriting. On a comprehensive dataset of words written by children aged from 3 to 11 years, we compare the judgment of human experts with a graph-based analysis, both with respect to classification and clustering. The results are promising and highlight the potential of graph-based methods for handwriting evaluation.
更多查看译文
关键词
graph,visuo-structural
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要