Journal of Frontiers of Computer Science and Technology ›› 2022, Vol. 16 ›› Issue (10): 2387-2394.DOI: 10.3778/j.issn.1673-9418.2102026

• Graphics and Image • Previous Articles     Next Articles

Modified Algorithm of Capsule Network for Classifying Small Sample Image

WANG Feilong1, LIU Ping1, ZHANG Ling2, LI Gang2,+()   

  1. 1. College of Data Science, Taiyuan University of Technology, Jinzhong, Shanxi 030600, China
    2. College of Software, Taiyuan University of Technology, Jinzhong, Shanxi 030600, China
  • Received:2021-02-06 Revised:2021-04-12 Online:2022-10-01 Published:2021-04-26
  • About author:WANG Feilong, born in 1996, M.S. candidate, student member of CCF. His research interest is image processing.
    LIU Ping, born in 1976, Ph.D. candidate, asso-ciate professor. Her research interest is big data of water resources.
    ZHANG Ling, born in 1985, Ph.D. candidate, lecturer, member of CCF. Her research interests include machine learning and image processing.
    LI Gang, born in 1980, Ph.D. candidate, asso-ciate professor, member of CCF. His research interests include artificial intelligence and vi-sual information processing.
  • Supported by:
    National Natural Science Foundation of China(61976150);Natural Science Foundation of Shanxi Province(201901D111091);Natural Science Foundation of Shanxi Province(201801D21135);University Science and Technology Innovation Project of Shanxi Province(JYTKJCX201943)


王飞龙1, 刘萍1, 张玲2, 李钢2,+()   

  1. 1.太原理工大学 大数据学院,山西 晋中 030600
    2.太原理工大学 软件学院,山西 晋中 030600
  • 通讯作者: + E-mail:
  • 作者简介:王飞龙(1996—),男,山西运城人,硕士研究生,CCF学生会员,主要研究方向为图像处理。
    李钢(1980—),男,内蒙古包头人,博士研究生,副教授,CCF 会员,主要研究方向为人工智能、视觉信息处理。
  • 基金资助:


In order to address the problem that the capsule network can not classify complex small sample images effectively, a classification model is proposed on the basis of fusing the improved Darknet with the capsule network. Firstly, the Darknet is upgraded containing both the shallow level extractor and the deep level extractor. The shallow level extractor adopts a 5×5 convolution kernel to capture long-distance edge contour features and the deep level extractor uses a 3×3 convolution kernel to capture deeper semantic features. Then, the extracted edge features and semantic features are fused to preserve effective features of images. Next, the capsule network is used to vectorize these effective features to work out the loss of spatial representation. Finally, L2 regularization is added in the loss function to avoid the over-fitting. Experimental results show that, on the small sample dataset, the classification accuracy of the proposed model is 28.51 percentage points and 24.40 percentage points higher than that of the models of the capsule network and the DCaps respectively, 21.57 percentage points and 18.02 percentage points higher than that of the ResNet50 and the Xception respectively. Hence it suggests that the method proposed in this paper gains a better performance in classifying complex small sample images. Meanwhile, on the large sample dataset, the classification accuracy of the proposed model has also been improved to a certain extent.

Key words: small sample image, capsule network, Darknet, L2 regularization, image classification



关键词: 小样本图像, 胶囊网络, Darknet, L2正则化项, 图像分类

CLC Number: