软件导刊2026，Vol.25Issue(1)：10-16,7.DOI:10.11907/rjdk.241869
基于RDEB-FCE模型的西夏文本检测研究
Research on Tangut Text Detection Based on RDEB-FCE Model
摘要
Abstract
A Xixia text detection method RDEB-FCE based on dilated convolution and attention guidance is proposed to address the problems of missed and false detections caused by the diverse scales and irregular shapes of text instances in current Xixia text detection tasks.The mod-el first uses Resnet50 as the backbone network and employs FPN structure to capture multi-scale features;Secondly,utilizing dilated convolu-tion to expand the receptive field of features and enhance the multi-scale capture capability of feature information,while adopting an efficient channel attention mechanism to adaptively adjust the weights of channel features,in order to improve the performance of the model in process-ing large-scale and high-resolution Western Xia text images;Finally,in the regression loss function,Smooth-L1 loss is replaced with Bal-anced L1 loss to improve the gradient of accurate samples and thus enhance the accuracy of text detection.The experimental results show that the accuracy of this method on the Xixiawen dataset constructed in the laboratory reaches 92.4％,which is a significant improvement compared to the current mainstream methods.关键词
西夏古籍/文本检测/注意力机制/空洞卷积/损失函数Key words
ancient books of Tangut/text detection/attention mechanism/empty convolution/loss function分类
信息技术与安全科学引用本文复制引用
张文静,史伟,赵心怡..基于RDEB-FCE模型的西夏文本检测研究[J].软件导刊,2026,25(1):10-16,7.基金项目
国家自然科学基金项目(62166030) （62166030）
