Proceedings of the 13th EAI International Conference on Mobile Multimedia Communications, Mobimedia 2020, 27-28 August 2020, Cyberspace

Research Article

Lightweight Deep Learning Model for Invoice Image Classification

Download568 downloads
  • @INPROCEEDINGS{10.4108/eai.27-8-2020.2295049,
        author={run  wang and Chonghu  Cheng and Yang  Meng and Yingyi  Sun and Jie  Yang and Guan  Gui},
        title={Lightweight Deep Learning Model for Invoice Image Classification},
        proceedings={Proceedings of the 13th EAI International Conference on Mobile Multimedia Communications, Mobimedia 2020, 27-28 August 2020, Cyberspace},
        publisher={EAI},
        proceedings_a={MOBIMEDIA},
        year={2020},
        month={11},
        keywords={image classification deep learning convolutional neural network computer vision},
        doi={10.4108/eai.27-8-2020.2295049}
    }
    
  • run wang
    Chonghu Cheng
    Yang Meng
    Yingyi Sun
    Jie Yang
    Guan Gui
    Year: 2020
    Lightweight Deep Learning Model for Invoice Image Classification
    MOBIMEDIA
    EAI
    DOI: 10.4108/eai.27-8-2020.2295049
run wang1, Chonghu Cheng1, Yang Meng1, Yingyi Sun2, Jie Yang1, Guan Gui1,*
  • 1: College of Telecommunications & Information Engineering Nanjing University of Posts and Telecommunications Nanjing 210003, China
  • 2: College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
*Contact email: guiguan@njupt.edu.cn

Abstract

Deep learning based image classification usually needs a large amount of data and computing resources to achieve better classification results. Hence, image classification for small data sets has attracted more and more attention in recent years. we proposed a lightweight deep learning model in this paper, which can be used for image classification on small datasets. The experimental results show that this model can achieve high accuracy classification with small data sets.