Increasing Offline Handwritten Chinese Character Recognition Using Separated Pre-Training Models: A Computer Vision Approach

被引:0
作者
He, Xiaoli [1 ]
Zhang, Bo [1 ]
Long, Yuan [1 ]
机构
[1] Sichuan Univ Sci & Engn, Sch Comp Sci, Zigong 643000, Peoples R China
关键词
machine learning; Chinese character recognition; convolutional auto-encoder; split modeling; NETWORK;
D O I
10.3390/electronics13152893
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Offline handwritten Chinese character recognition involves the application of computer vision techniques to recognize individual handwritten Chinese characters. This technology has significantly advanced the research in online handwriting recognition. Despite its widespread application across various fields, offline recognition faces numerous challenges. These challenges include the diversity of glyphs resulting from different writers' styles and habits, the vast number of Chinese character labels, and the presence of morphological similarities among characters. To address these challenges, an optimization method based on a separated pre-training model was proposed. The method aims to enhance the accuracy and robustness of recognizing similar character images by exploring potential correlations among them. In experiments, the HWDB and Chinese Calligraphy Styles by Calligraphers datasets were employed, utilizing precision, recall, and the Macro-F1 value as evaluation metrics. We employ a convolutional self-encoder model characterized by high recognition accuracy and robust performance. The experimental results demonstrated that the separated pre-training models improved the performance of the convolutional auto-encoder model, particularly in handling error-prone characters, resulting in an approximate 6% increase in precision.
引用
收藏
页数:13
相关论文
共 25 条
[1]   Arabic handwriting recognition system using convolutional neural network [J].
Altwaijry, Najwa ;
Al-Turaiki, Isra .
NEURAL COMPUTING & APPLICATIONS, 2021, 33 (07) :2249-2261
[2]  
[Anonymous], 1980, GB2312-1980
[3]   The Handwritten Chinese Character Recognition Uses Convolutional Neural Networks with the GoogLeNet [J].
Bi, Ning ;
Chen, Jiahao ;
Tan, Jun .
INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2019, 33 (11)
[4]   Zero-shot Handwritten Chinese Character Recognition with hierarchical decomposition embedding [J].
Cao, Zhong ;
Lu, Jiang ;
Cui, Sen ;
Zhang, Changshui .
PATTERN RECOGNITION, 2020, 107
[5]   Adaptive embedding gate for attention-based scene text recognition [J].
Chen, Xiaoxue ;
Wang, Tianwei ;
Zhu, Yuanzhi ;
Jin, Lianwen ;
Luo, Canjie .
NEUROCOMPUTING, 2020, 381 :261-271
[6]   A new adaptive filtering method for removing salt and pepper noise based on multilayered PCNN [J].
Deng, Xiangyu ;
Ma, Yide ;
Dong, Min .
PATTERN RECOGNITION LETTERS, 2016, 79 :8-17
[7]  
Diao XL, 2022, Arxiv, DOI arXiv:2207.05842
[8]   A generalized ensemble approach based on transfer learning for Braille character recognition [J].
Elaraby, Nagwa ;
Barakat, Sherif ;
Rezk, Amira .
INFORMATION PROCESSING & MANAGEMENT, 2024, 61 (01)
[9]   Characters as graphs: Interpretable handwritten Chinese character recognition via Pyramid Graph Transformer [J].
Gan, Ji ;
Chen, Yuyan ;
Hu, Bo ;
Leng, Jiaxu ;
Wang, Weiqiang ;
Gao, Xinbo .
PATTERN RECOGNITION, 2023, 137
[10]   Compressing the CNN architecture for in-air handwritten Chinese character recognition [J].
Gan, Ji ;
Wang, Weiqiang ;
Lu, Ke .
PATTERN RECOGNITION LETTERS, 2020, 129 :190-197