Electronic Science and Technology ›› 2019, Vol. 32 ›› Issue (2): 51-55.doi: 10.16180/j.cnki.issn1007-7820.2019.02.011

Previous Articles     Next Articles

Minority Headdress Recognition Based on Convolutional Neural Network

LI Rongrui,SHI Lin,ZHAO Wei   

  1. Faculty of Information Engineering and Automation, Kunming University of Science and Technology,Kunming 650500, China
  • Received:2018-01-22 Online:2019-02-15 Published:2019-01-02
  • Supported by:
    Yunnan Talent Training Fund(KKSY201303074)


The feature point of the traditional headdress image recognition method was extracted by the researchers manually. The system has some disadvantages including tedious preprocessing steps, high sample requirement and low accuracy. To solve these problems, the convolutional neural network was constructed to learn the deep features from image data. The CNN model selected the ReLU function with better sparsity to adjust the output, and used back propagation algorithm to optimize the network parameters.The softmax classifier was identified after the CNN model. The experimental results showed that the recognition rate of the system to the test set of headdress reached 96.25%. This method was proved to have good recognition accuracy and recognition efficiency.

Key words: CNN, minority headdress, feature extraction, image recognition, deep learning, Caffe

CLC Number: 

  • TP391