Art

J-GLOBAL ID：202102269389545329   Reference number：21A0423756

CNN and 2D BLSTM for Local Feature Extraction in Handwritten Mathematical Expression Recognition

手書き数式認識におけるCNNと2D BLSTMによる局所特徴抽出

Author (4)： MORIZUMI KEI (東京農工大 大学院工学府) ,  NGUYEN Cuong Tuan (東京農工大 大学院工学府) ,  SHIMIZU IKUKO (東京農工大 大学院工学府) ,  NAKAGAWA MASAKI (東京農工大 大学院工学府)
Material： 電子情報通信学会技術研究報告(Web)  (IEICE Technical Report (Web))
Volume： 120  Issue： 300(PRMU2020 38-68)  Page： 105-110 (WEB ONLY)  Publication year： Dec. 10, 2020 
JST Material Number： U2030A  ISSN： 2432-6380  Document type： Proceedings
Article type： 原著論文  Country of issue： Japan (JPN)  Language： JAPANESE (JA)

Thesaurus term： *handwritten character recognition ,  *formula ,  neural network(biomodel) ,  machine learning ,  supervised learning ,  feature extraction ,  combinatorial optimization problem ,  document image ,  image processing
Semi thesaurus term： Long Short Term Memory Neural Network ,  convolutional neuralnetwork ,  mathematical formula

JST classification (1)： Pattern recognition  (JE07000S)

Reference (9)：

• Y. Z. Zhe Li , Lianwen Jin , Songxuan Lai, “Improving Attention-Based Handwritten Mathematical Expression Recognition with Scale Augmentation and Drop Attention,” Proc. 17th Int. Conf. Front. Handwrit. Recognition, pp. 175-080, 2020.
• M. Luong, H. Pham, and C. D. Manning, “Effective Approaches to Attention-based Neural Machine Translation,” Proc. 2015 Conf. Empir. Methods Nat. Lang. Process., p. 1412-1421, 2015.
• J. Zhang et al., “Watch, attend and parse: An end-to-end neural network based approach to handwritten mathematical expression recognition,” Pattern Recognit., vol. 71, pp. 196-206, Nov. 2017, doi:10.1016/j.patcog.2017.06.017.
• Y. Deng, A. Kanervisto, J. Ling, and A. M. Rush, “Image-to-Markup Generation with Coarseto-Fine Attention,” 34th Int. Conf. Mach. Learn. ICML 2017, vol. 3, pp. 1631-1640, Sep. 2016.
• T.-N. Truong, C. T. Nguyen, K. M. Phan, and M. Nakagawa, “Improvement of End-to-End Offline Handwritten Mathematical Expression Recognition by Weakly Supervised Learning,” Proc. 17th Int. Conf. Front. Handwrit. Recognit., pp. 181-186, 2020.

Terms in the title (5)： 手書き ,  数式 ,  CNN ,  2D ,  局所特徴