机械与电子2026，Vol.44Issue(1)：28-34,7.
基于Swin-UNet的破损碑刻文字识别方法
A Character Recognition Method for Damaged Inscriptions Based on Swin-UNet
摘要
Abstract
This paper presents a method for recognizing damaged stone inscription characters based on Swin-UNet.To accurately extract textual information from stone inscriptions,the Swin transformer ar-chitecture is employed to replace the down-sampling and up-sampling processes of the original U-Net structure in the segmentation task.The CBAM(Convoluted Basin Aggregation Module)and SENet mod-ules are integrated to optimize the feature fusion.The loss function is also refined using a weighted cross-entropy loss.Stone inscription characters in natural environments often suffer from various forms of degra-dation.Consequently,a semantic segmentation database for these characters is constructed based on real-world data sets,and an algorithm is designed to identify damaged characters by leveraging this database.Experimental results demonstrate that on real stone inscription images,the recognition accuracy reaches 32.60%for missing up to two strokes,64.20%when identifying the first five correct characters,and 77.20%for the first ten characters.Compared with other semantic segmentation models,the proposed method achieves more accurate stroke-level segmentation and yields superior performance.关键词
碑刻文字/文字识别/Swin Transformer/U-Net/语义分割Key words
stone inscription characters/character recognition/Swin Transformer/U-Net/semantic segmenta-tion分类
信息技术与安全科学引用本文复制引用
李晓亮,李光亚,孟志琳..基于Swin-UNet的破损碑刻文字识别方法[J].机械与电子,2026,44(1):28-34,7.基金项目
科技部国家重点研发计划(2020YFB2009102) （2020YFB2009102）
