Electronic Science and Technology ›› 2020, Vol. 33 ›› Issue (5): 1-8.doi: 10.16180/j.cnki.issn1007-7820.2020.05.001

    Next Articles

Image Super-resolution Algorithm Based on SqueezeNet Convolution Neural Network

QIN Xing1,GAO Xiaoqi1,CHEN Bin2   

  1. 1. School of Electronic and Information,Hangzhou Dianzi University,Hangzhou 310018,China
    2. School of Computer Science and Technoogy,Hangzhou Dianzi University,Hangzhou 310018,China
  • Received:2019-03-21 Online:2020-05-15 Published:2020-06-02
  • Supported by:
    National Key R & D Program of China(2016YFB1000400);Zhejiang Natural Science Foundation(LY17F020023)


In order to effectively improve the resolution of depth image, the study proposed a convolutional neural network model based on the Fire Module by referring to the classic SqueezeNet network structure. The proposed algorithm implemented mapping and transformation directly from low-resolution images to high-resolution images. As a nonlinear mapping module of the network, Fire Module learned the deep features of the image while reducing the parameters. To avoid interpolation preprocessing, a deconvolution layer was introduced in the output layer of the network to achieve a final 3 times up-sampling and high resolution image output. Experiments showed that the super-resolution image obtained by the deconvolution algorithm of the convolutional neural network model based on Fire Module was richer in detail, and the evaluation of objective index PSNR value and SSIM value was also superior to other algorithms.

Key words: image processing, super-resolution reconstruction, convolution neural network, deconvolution, residual block, inception block

CLC Number: 

  • TP391