西夏文字的多层掩码识别方法  

A multi-layer mask recognition method for Tangut characters

作　　者：马金林 闫琦 马自萍 MA Jin-lin;YAN Qi;MA Zi-ping(College of Computer Science and Engineering,North Minzu University,Yinchuan 750021;The Key Laboratory of Images and Graphics Intelligent Processing of State Ethnic Affairs Commission,Yinchuan 750021;School of Mathematics and Information Science,North Minzu University,Yinchuan 750021,China)

机构地区：[1]北方民族大学计算机科学与工程学院,宁夏银川750021 [2]图像图形智能信息处理国家民委重点实验室,宁夏银川750021 [3]北方民族大学数学与信息科学学院,宁夏银川750021

出　　处：《计算机工程与科学》2024年第12期2227-2238,共12页Computer Engineering & Science

基　　金：国家自然科学基金(62462001);宁夏自然科学基金(2023AAC03264);北方民族大学中央高校基本科研业务费专项资金资助(2023ZRLG02);宁夏高等学校科学研究项目(NYG2024066)。

摘　　要：针对现有方法对模糊、残缺西夏文字识别能力较差的问题,提出西夏文字识别模型MMSFTR。首先,提出多层掩码学习策略,分层次提取字符关键特征,帮助模型更有效地理解西夏文字内部结构,提高对复杂西夏文字的特征描述能力。其次,设计多尺度特征融合模块,以提取更丰富的多尺度特征。然后,提出通道自适应注意力模块,更好地选择和关注特定通道的信息,并设计掩码注意力模块改善模型感知能力。最后,设计特征增强模块,对网络进行多层次特征优化,并进行深层次特征增强。MMSFTR通过4个模块的协同作业,使得模型达到了预期效果。实验结果显示:MMSFTR在TCD-E数据集上达到99.40%的识别准确率,有效提升了对模糊、残缺西夏文字的识别效果。Aiming at the problem of poor recognition ability of existing methods for fuzzy and mutilated Tangut characters,a Tangut character recognition model MMSFTR is proposed.Firstly,a multi-layer mask learning strategy is introduced to extract key character features in a hierarchical manner,assisting the model in understanding the internal structure of the Tangut characters more efficiently,and improving its ability to describe complex features of Tangut characters.Secondly,a multi-scale feature fusion module is designed to extract richer multi-scale features.Then,a channel adaptive attention module is proposed to better select and focus on information from specific channels.A mask attention module is also designed to improve the model's perception capabilities.Finally,a feature enhancement module is designed to optimize multi-level features of the network and enhance deep-level features.Through the collaborative work of these 4 modules,MMSFTR achieves the desired results.Experimental results show that MMSFTR achieves a recognition accuracy of 99.40%on the TCD-E dataset,effectively enhancing the recognition effect of fuzzy and mutilated Tangut characters.

关 键 词：西夏文字识别 多尺度特征融合 掩码学习 逆残差块 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]