Exploiting Gabor Feature Extraction Method for Chinese Character Writing Quality Evaluation

作     者：Zhixiao Wang Wenyao Yan Mingtao Guo Jiulong Zhang 

作者机构：School of Computer Science and Engineering Xi'an University of Technology Xi'an 710048 China Shaanxi Key Laboratory Xi'an of Network Computing and Security Technology China School of Data Science and Computer Xi'an innovation college of Yan'an University Xi'an 710100 China 

出 版 物：《Journal of Physics: Conference Series》 

年 卷 期：2020年第1575卷第1期

学科分类：07[理学] 0702[理学-物理学] 

摘      要：The automatic evaluation of Chinese character writing quality has a wide application prospect. Most of the existing evaluation methods of Chinese character writing quality are based on radical segmentation and feature judgment, which require the high accuracy of Chinese character segmentation. However, there are many problems in the real handwriting, such as continuous writing, uneven strength of writing, personalized writing style and so on, which lead to the difficulty of segmentation in the ordinary handwriting. To solve the above problems, we propose an effective method based on image texture where the uniformity of writing lines and writing style is taken as an effective criterion. In our method, Gabor transform is used to extract the image features of writing samples, and finally the statistical learning method of support vector machine is used to effectively evaluate the writing quality. Experiments on multiple real datasets including CHAED show that our method is effective and accurate. The advantage of this method is that it does not need to segment fonts, and the cost of global feature extraction is small.