Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 36 min ago
Peer-reviewedCC BY 4.0PLOS One

ISD-YOLO: A lightweight and efficient feature extraction network for invoice seal detection

  • Xiaosi Song1
  • Xiaohong Zhao2
  • Caihua Ma
  • Wenpei Xu
  • Peng Shen
  1. 1Hengshui College of Vocational Technology, Hengshui, China
  2. 2North China Institute of Aerospace Engineering, Langfang, China
Open at sourcePDFDOICite

Abstract

Invoice seal detection plays an important role in intelligent invoice processing by improving review efficiency and reducing potential financial risks. However, existing methods still face challenges in multi-scale feature representation, complex background interference, and balancing detection accuracy with computational efficiency. In this study, a lightweight detection model, ISD-YOLO, is proposed for invoice seal detection. Specifically, the C3k2-ConvFormer-CGLU module (C3k2_CFC) is designed to enhance multi-scale feature representation by combining local feature enhancement and gated feature selection. A C2BRA module based on bi-level routing attention is introduced to improve the extraction of discriminative seal features by dynamically selecting important regions. In addition, a deformable attention module (DAttention) is incorporated to enhance the focus on key regions and reduce background interference. Furthermore, a lightweight detection head (EfficientHead) is developed to reduce computational complexity while maintaining detection performance, providing potential for resource-constrained applications. Experiments were conducted on a dataset consisting of public seal images and real invoice images. Compared with the baseline model, ISD-YOLO improves mAP50 and mAP50:95 by 2.1% and 2.3%, respectively. Compared with existing detection methods, ISD-YOLO achieves an F1-score of 95.3% and an mAP50 of 97.2%, while requiring only 2.3 M parameters and 5.0 GFLOPs. The results demonstrate that ISD-YOLO achieves a favorable balance between detection accuracy and computational efficiency under the evaluated invoice seal detection conditions. Its lightweight design indicates potential for resource-constrained applications, while further validation under broader scenarios and on actual edge devices is still required.

Related

  1. Cross-level attention and lightweight feature extraction for improved tomato ripeness detection in complex greenhouse environments
    Xiao Cui, Jisheng Liu, Yujin Guo +4
    Frontiers in Plant SciencePeer-reviewedCC BY 4.0Plant biologyFrontiersCrossref
  2. WSD-YOLO: A lightweight YOLO-based model with enhanced feature representation for maize pest detection
    Shenming Qu, Zhiheng Liu, Huazhen Zhao +2
    PLOS OnePeer-reviewedCC BY 4.0Plant biologyPLOS
  3. Enhancing medical image segmentation with HCE-Net: A heterogeneous feature collaborative extraction network
    Guoqing Zhu, Hongzhi Li, Han Cui +2
    PLOS OnePeer-reviewedCC BY 4.0Full textNeurosciencePhysiologyPLOSPMC
  4. MEF-TBN: Multi-exposure image fusion approach based on a three-branch network for feature extraction and color enhancement
    Chunmeng Wang, Wenxiang Zhang, Quan Zhang +1
    PLOS OnePeer-reviewedCC BY 4.0Full textNeurosciencePLOS
  5. Efficient-tomato: a high-precision and lightweight method for cherry tomato ripeness and disease detection
    Yunchang Zheng, Mengfan Wang, Jiacheng Sun +2
    Frontiers in Plant SciencePeer-reviewedCC BY 4.0Full textPlant biologyCrossrefEurope PMCPMC

Cite

BibTeXRIS
BibTeX
@article{song2026isdyolo,
  title = {{ISD-YOLO: A lightweight and efficient feature extraction network for invoice seal detection}},
  author = {Xiaosi Song and Xiaohong Zhao and Caihua Ma and Wenpei Xu and Peng Shen},
  journal = {PLOS One},
  year = {2026},
  month = sep,
  doi = {10.1371/journal.pone.0358190},
  url = {https://doi.org/10.1371/journal.pone.0358190},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - ISD-YOLO: A lightweight and efficient feature extraction network for invoice seal detection
AU  - Xiaosi Song
AU  - Xiaohong Zhao
AU  - Caihua Ma
AU  - Wenpei Xu
AU  - Peng Shen
PY  - 2026
DA  - 2026/09/11
JO  - PLOS One
DO  - 10.1371/journal.pone.0358190
UR  - https://doi.org/10.1371/journal.pone.0358190
AB  - Invoice seal detection plays an important role in intelligent invoice processing by improving review efficiency and reducing potential financial risks. However, existing methods still face challenges in multi-scale feature representation, complex background interference, and balancing detection accuracy with computational efficiency. In this study, a lightweight detection model, ISD-YOLO, is proposed for invoice seal detection. Specifically, the C3k2-ConvFormer-CGLU module (C3k2_CFC) is designed to enhance multi-scale feature representation by combining local feature enhancement and gated feature selection. A C2BRA module based on bi-level routing attention is introduced to improve the extraction of discriminative seal features by dynamically selecting important regions. In addition, a deformable attention module (DAttention) is incorporated to enhance the focus on key regions and reduce background interference. Furthermore, a lightweight detection head (EfficientHead) is developed to reduce computational complexity while maintaining detection performance, providing potential for resource-constrained applications. Experiments were conducted on a dataset consisting of public seal images and real invoice images. Compared with the baseline model, ISD-YOLO improves mAP50 and mAP50:95 by 2.1% and 2.3%, respectively. Compared with existing detection methods, ISD-YOLO achieves an F1-score of 95.3% and an mAP50 of 97.2%, while requiring only 2.3 M parameters and 5.0 GFLOPs. The results demonstrate that ISD-YOLO achieves a favorable balance between detection accuracy and computational efficiency under the evaluated invoice seal detection conditions. Its lightweight design indicates potential for resource-constrained applications, while further validation under broader scenarios and on actual edge devices is still required.
SN  - 1932-6203
ER  -