典型文献
Synthetic Data Generation and Shuffled Multi-Round Training Based Offline Handwritten Mathematical Expression Recognition
文献摘要：
Offline handwritten mathematical expression recognition is a challenging optical character recognition(OCR)task due to various ambiguities of handwritten symbols and complicated two-dimensional structures.Recent work in this area usually constructs deeper and deeper neural networks trained with end-to-end approaches to improve the performance.However,the higher the complexity of the network,the more the computing resources and time required.To improve the performance without more computing requirements,we concentrate on the training data and the training strategy in this paper.We propose a data augmentation method which can generate synthetic samples with new LaTeX notations by only using the official training data of CROHME.Moreover,we propose a novel training strategy called Shuffled Multi-Round Training(SMRT)to regularize the model.With 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.
文献关键词：
中图分类号：
作者姓名：
Lan-Fang Dong;Han-Chao Liu;Xin-Ming Zhang
作者机构：
School of Computer Science and Technology,University of Science and Technology of China,Hefei 230022,China
文献出处：
引用格式：
[1]Lan-Fang Dong;Han-Chao Liu;Xin-Ming Zhang-.Synthetic Data Generation and Shuffled Multi-Round Training Based Offline Handwritten Mathematical Expression Recognition)[J].计算机科学技术学报（英文版）,2022(06):1427-1443
A类：
Shuffled,Handwritten
B类：
Synthetic,Data,Generation,Multi,Round,Training,Based,Offline,Mathematical,Expression,Recognition,handwritten,mathematical,expression,recognition,challenging,optical,character,OCR,task,due,various,ambiguities,symbols,complicated,dimensional,structures,Recent,this,area,usually,constructs,deeper,neural,networks,trained,end,approaches,improve,performance,However,higher,complexity,more,computing,resources,required,To,without,requirements,concentrate,training,data,strategy,paper,We,propose,augmentation,method,which,can,synthetic,samples,new,LaTeX,notations,by,only,using,official,CROHME,Moreover,novel,called,SMRT,regularize,With,generated,shuffled,multi,round,achieve,state,art,result,accuracy,respectively,attention,encoder,decoder,models,offline
AB值：
0.599737
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
