Article Details

Title · Authors · Abstract · Keywords · DOI · References

Research on P-ENet Invoice Text Detection Algorithm Based on Enhanced Pyramid Structure

LIU Wenjie, LI Zhongwen, WANG Yunfeng, ZHU Li

(Army Logistics Academy, Chongqing 400031, China)

Section:Computer Technology · 2025, Vol. 9, No. 11 · Pages:102-105,113 · 2096-4706(2025)11-0102-05 · CLC number:TP391.4 · Document code:A · DOI:10.19850/j.cnki.2096-4706.2025.11.020

Abstract

As an indispensable document in commercial economic activities, invoices are crucial to financial management. However, the traditional invoice reimbursement process is cumbersome and inefficient. In recent years, with the rapid development of the national economy, the frequency of use of invoices has increased dramatically, making the automatic processing of invoices one of the key means to improve the efficiency of business operations. Therefore, aiming at the field of invoice text detection, this paper conducts scientific research on the problems of low accuracy and slow running speed of the current popular text detection algorithms. Based on the FPN architecture, this paper uses EfficientNet and ASPP modules to construct a new invoice text detection network P-ENet with enhanced pyramid structure. Then, experiments are carried out on the self-annotated invoice data set. The results show that the improved model has an Intersection over Union of 86.89%, a Precision of 91.36%, and a Recall of 85.43% on the invoice data set. Both have achieved a high level, and the running speed of the model has also been significantly improved.

Keywords

text detection; invoice recognition; EfficientNet; spatial pyramid

References

  1. [1] Jing Tao, Wang Zhong Optical Character Recognition Technology and Prospects [J]. Computer Engineering, 2003 (2): 1-2+80
  2. [2] SUN B,HUA S J,LI S T,et al. Graph-Matching-Based Character Recognition for Chinese Seal Images [J].Science China Information Sciences,2019,62(9):37-50.
  3. [3] TIAN Z,HUANG W L,HE T,et al. Detecting Text in Natural Image with Connectionist Text Proposal Network [J].Computer Vision-ECCV 2016,2016,38(11):2276-2290.
  4. [4] ZHOU X Y,YAO C,WEN H,et al. EAST: An Efficient and Accurate Scene Text Detector [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Honolulu:IEEE,2017:2642-2651.
  5. [5] WANG W H,XIE E,LI X,et al. Shape Robust Text Detection With Progressive Scale Expansion Network [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Long Beach:IEEE,2019:9328-9337.
  6. [6] HUANG Z H,XU W,YU K. Bidirectional LSTM-CRF Models for Sequence Tagging [J/OL].arXiv:1508.01991 [cs.CL].[2024-11-03].https://doi.org/10.48550/arXiv.1508.01991.
  7. [7] SIMONYAN K,ZISSERMAN A. Very Deep Convolutional Networks for Large-Scale Image Recognition [J/OL].arXiv:1409.1556 [cs.CV].[2024-10-26].https://doi.org/10.48550/arXiv.1409.1556.
  8. [8] REN S Q,HE K M,GIRSHICK R,et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6),1137-1149.
  9. [9] RONNEBERGER O. Invited Talk: U-Net Convolutional Networks for Biomedical Image Segmentation [C]//Bildverarbeitung für die Medizin 2017.Heidelberg:Springer,2017:3.
  10. [10] HE K M,ZHANG X Y,REN X Q,et al. Deep Residual Learning for Image Recognition [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas:IEEE,2016:770-778.
  11. [11] TAN M X,LE Q V. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks [J/OL].arXiv:1905.11946 [cs.LG].[2024-10-20].https://doi.org/10.48550/arXiv.1905.11946.
  12. [12] HOWARD A G,ZHU G L,CHEN B,et al. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications [J/OL].arXiv:1704.04861 [cs.CV].[2024-10-16].https://doi.org/10.48550/arXiv.1704.04861.
  13. [13] CHEN L-C,PAPANDREOU G,SCHROFF F,et al. Rethinking Atrous Convolution for Semantic Image Segmentation [J/OL].arXiv:1706.05587 [cs.CV].[2024-10-19].https://doi.org/10.48550/arXiv.1706.05587.

Funding

Comprehensive Research Project on Army Equipment of the Chinese People's Liberation Army (Zhuang Zong [2023] No. 1763); Youth Fund Project of the PLA Army Service College (LQ-QN-202419)

About the authors

Liu Wenjie (1995-), male, Han ethnicity, from Dingxi, Gansu, teaching assistant, master's degree, research direction: intelligent finance; Li Zhongwen (1985-), male, Han ethnicity, from Xiangyang, Hubei, lecturer, master's degree, research direction: intelligent finance; Wang Yunfeng (1995-), male, Han ethnicity, from Wushan, Chongqing, teaching assistant, master's degree, research direction: intelligent finance; Zhu Li (1987-), male, Han ethnicity, from Xiangyang, Hubei, associate professor, master's degree, research direction: intelligent finance.