Synthetic Data Generation and Shuffled Multi-Round Training Based Offline Handwritten Mathematical Expression Recognition

作     者：Lan-Fang Dong Han-Chao Liu Xin-Ming Zhang 董兰芳;刘汉超;张信明

作者机构：School of Computer Science and TechnologyUniversity of Science and Technology of ChinaHefei 230022China 

出 版 物：《Journal of Computer Science & Technology》 (计算机科学技术学报（英文版）)

年 卷 期：2022年第37卷第6期

页      面：1427-1443页

核心收录：

学科分类：08[工学] 0835[工学-软件工程] 081202[工学-计算机软件与理论] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：the National Key Research and Development Program of China No.2020YFB1313602 

主　　题：handwritten mathematical expression recognition offline synthetic data generation training strategy 

摘      要：Offline handwritten mathematical expression recognition is a challenging optical character recognition(OCR)task due to various ambiguities of handwritten symbols and complicated two-dimensional *** work in this area usually constructs deeper and deeper neural networks trained with end-to-end approaches to improve the ***,the higher the complexity of the network,the more the computing resources and time *** improve the performance without more computing requirements,we concentrate on the training data and the training strategy in this *** propose a data augmentation method which can generate synthetic samples with new LaTeX notations by only using the official training data of ***,we propose a novel training strategy called Shuffled Multi-Round Training(SMRT)to regularize the *** the generated data and the shuffled multi-round training strategy,we achieve the state-of-the-art result in expression accuracy,i.e.,59.74%and 61.57%on CROHME 2014 and 2016,respectively,by using attention-based encoder-decoder models for offline handwritten mathematical expression recognition.