Journal of Xidian University ›› 2020, Vol. 47 ›› Issue (2): 39-45.doi: 10.19665/j.issn1001-2400.2020.02.006

Previous Articles     Next Articles

Urine cell image classification algorithm based on the squeeze and excitation mechanism

SONG Jianfeng1,WEI Yue1,MIAO Qiguang1(),QUAN Yining1,CHEN Yusheng2   

  1. 1.School of Computer Science and Technology, Xidian University, Xi’an 710071, China
    2.Unit 96963 of the People’s Liberation Army of China, Beijing 100000, China
  • Received:2019-11-08 Online:2020-04-20 Published:2020-04-26
  • Contact: Qiguang MIAO


In order to solve the classification problem on the urine-forming sub-cell images, a urine cell image classification algorithm based on the Squeeze-and-Excitation GoogLeNet is proposed. The algorithm uses the feature recalibration mechanism and brings about significant improvement in the useful feature for the current task through squeeze and excitation operations, which explicitly models interdependencies between cell feature channels learned by the Inception architecture during the training process. On the urine cell datasets, comparative experimental results show that the algorithm provides a better classification effect, which improves the accuracy of classification by 3% and the recall rate by 1% at the similar speed of the GoogLeNet network.

Key words: urine cell, squeeze and excitation, feature recalibration, image classification

CLC Number: 

  • TP37