Scholarlink

<p>Jiandu images often exhibit dense text, large scale variations, random spatial distribution, and slight geometric deformation, which pose significant challenges to character-level detection. To address these issues, this paper proposes a DDSF-YOLO framework for Jiandu text detection. Specifically, the DBS module is introduced into the backbone network to adaptively adjust the receptive field through deformable convolution. During feature extraction, the DFF module is used to fuse local details with global semantics. In the feature pyramid, SAFMN-FPN is incorporated together with learnable upsampling to enhance multi-scale feature representation. In addition, a small-object detection head is added to improve the recall of dense small characters. Experimental results show that the proposed method achieves 97.5% precision, 95.8% recall, and 96.6% F1-score on the JianduMix-dataset, outperforming multiple comparative methods. The results demonstrate that the proposed method can effectively improve text detection performance in complex Jiandu scenes.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

DDSF-YOLO for accurate multi-scale text detection in Jiandu images

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月19日

查看全文
  • Qiang Zhang,
  • Yutong Li,
  • Chenyang Wang,
  • Teng Wan,
  • Shuo Feng,
  • Jiazhen Qin,
  • Ying Qi

摘要

Jiandu images often exhibit dense text, large scale variations, random spatial distribution, and slight geometric deformation, which pose significant challenges to character-level detection. To address these issues, this paper proposes a DDSF-YOLO framework for Jiandu text detection. Specifically, the DBS module is introduced into the backbone network to adaptively adjust the receptive field through deformable convolution. During feature extraction, the DFF module is used to fuse local details with global semantics. In the feature pyramid, SAFMN-FPN is incorporated together with learnable upsampling to enhance multi-scale feature representation. In addition, a small-object detection head is added to improve the recall of dense small characters. Experimental results show that the proposed method achieves 97.5% precision, 95.8% recall, and 96.6% F1-score on the JianduMix-dataset, outperforming multiple comparative methods. The results demonstrate that the proposed method can effectively improve text detection performance in complex Jiandu scenes.