SSRScientific and Social Research2661-43322981-9946Bio-Byword Scientific Publishing Pty. Ltd.10.26689/ssr.v7i8.11983ArticleResearch and Practice of Multi-dimensional Chinese Character Quantification Evaluation Methodshttps://artdesignp.com/journal/SSR/7/8/10.26689/ssr.v7i8.11983DengPeng,YangGuiying2025782025-09-17Addressing the pain points of traditional Chinese character evaluation, which is highly subjective and lacks quantitative standards, this paper proposes a three-dimensional intelligent quantitative evaluation model for Chinese characters based on “accuracy—balance—standardization”, transitioning from experience-driven to data-driven evaluation: improving multi-model convolutional neural networks to extract stroke keypoints for accuracy assessment, combining image moments with cosine similarity to measure center of gravity deviation for balance evaluation, and using 3×3 grid pixel density ratios to characterize structural framework for standardization measurement. The model operates in a closed-loop system of “recognition—quantification—fuzzy comprehensive evaluation”, enhancing recognition accuracy through hard voting, automatically calibrating the scoring range using the “best-worst sample set”, and obtaining intelligent weights of 39:32:29 through backpropagation training. Experiments on four types of samples from the CASIA-HWDB1.1 and custom datasets show that the average error between the model and expert scores under intelligent weights is significantly lower than that of the two fixed weights, providing a practical quantitative evaluation tool for Chinese character education and cultural heritage.

Xiao X, Li CC, 2022, Research progress on handwritten Chinese character evaluation methods. Computer Engineering and Application, 58(2): 27–42.

Zhuang CB, Jin LW, 2005, An Intelligently Verified Algorithm for Correctness and Calligraphy of Online Handwritten Chinese Characters. Proceedings of the 12th National Annual Conference on Signal Processing (CCSP-2005).

Han RF, An WH, Xun ED, et al., 2016, Real-time Grading Judgement for Stroke Quality in Chinese Character Handwriting. Journal of Computer Applications, 36(S1): 281–285.

Yu K, Wu JQ, Zhuang YT, Calligraphic Character Retrieval Based on Skeleton Similarity. Journal of Computer-Aided Design & Computer Graphics, 21(6):746–751.

Wu CZ, 2017, Research and Implementation of Evaluation System of Chinese Calligraphy Copy, thesis, South China University of Technology.

Ge JM, 2016, Aesthetic Evaluation of Robot Calligraphy Based on Probability Distribution, thesis, Xiamen University.

Zhuang ZM, 2019, Handwritten Chinese Character Recognition and Aesthetic Grading Based on Deep Learning, thesis, Beijing University of Posts and Telecommunications.

Deng P, 2020, Research on Multi-feature Fusion Sample R, thesis, Recognition and Evaluation Model of Chinese Character Handwriting, thesis, Chongqing University. https://doi.org/10.27670/d.cnki.gcqdu.2020.001457