HchMER:混合人机智能的手写数学表达式识别方法  

HchMER:Hybrid Human-machine Intelligence Method for Handwritten Mathematical Expression Recognition

作　　者：康文惠 黄进[1] 仝青山 付强 田丰[1] 戴国忠[1] KANG Wen-Hui;HUANG Jin;TONG Qing-Shan;FU Qiang;TIAN Feng;DAI Guo-Zhong(Beijing Key Laboratory of Human-computer Interaction(Institute of Software,Chinese Academy of Sciences),Beijing 100190,China;School of Computer Science and Technology,University of Chinese Academy of Sciences,Beijing 100049,China)

机构地区：[1]人机交互北京市重点实验室(中国科学院软件研究所),北京100190 [2]中国科学院大学计算机科学与技术学院,北京100049

出　　处：《软件学报》2025年第2期915-938,共24页Journal of Software

基　　金：国家自然科学基金(62172397);中国科学院青年创新促进会项目(20200113)。

摘　　要：随着人工智能和端到端识别方法在手写数学表达式识别上的应用,数学表达式识别准确率有了明显的提高.然而,与公开数据集上的测试不同,实际应用中人的参与为识别算法引入了更多的不确定因素,如个性化的笔画信息、包含歧义的手写字符,以及不确定的公式结构等,影响了识别算法的性能.为此,提出了一种混合人机智能的手写数学表达式识别方法HchMER.该方法借助手写数学公式识别算法、知识库和用户反馈,增强机器对用户输入的数学表达式的理解,从而提升手写数学表达式的编辑速度和准确率.为了验证HchMER的有效性,将其分别与MyScript Math Recognition(MyScript)算法,以及一个成熟的商用产品“Microsoft Ink Equation”(InkEquation)进行了比较.实验结果表明,HchMER在准确率上较MyScript和InkEquation分别提高了23.2%和26.51%.在平均完成时间上,HchMER比MyScript增加了44.46%(9.6 s),但是比InkEquation降低了11.48%(4.05 s).同时,被试在问卷调查和半结构化访谈中对HchMER给予了肯定.With the application of artificial intelligence(AI)and end-to-end recognition methods in handwritten mathematical expression recognition,there has been a significant improvement in recognition accuracy.However,in contrast to tests on public datasets,real-world applications involving human input introduce more uncertain factors into recognition algorithms in practice.Factors such as personalized stroke information,ambiguous handwritten characters,and uncertain formula structures can significantly impact the performance of the recognition method.To address these challenges,HchMER,a hybrid human-machine intelligence method for handwritten mathematical expression recognition,is proposed.HchMER combines handwritten mathematical formula recognition algorithms,knowledge bases,and user feedback to enhance the machine's comprehension of user-input mathematical expressions,thereby improving the editing speed and accuracy of handwritten mathematical expressions.To assess the effectiveness of HchMER,it is compared with MyScript Math Recognition(MyScript)and a mature commercial product named“Microsoft Ink Equation”(InkEquation).Results show that HchMER outperformed MyScript and InkEquation in accuracy by 23.2%and 26.51%,respectively.In terms of average completion time,HchMER exceeded MyScript by 44.46%(9.6 s)but fell short of InkEquation by 11.48%(4.05 s).Furthermore,participants affirm HchMER in a questionnaire survey and semi-structured interviews.

关 键 词：人机混合智能 草图理解 在线手写数学表达式识别 用户界面 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]