eduzhai > Applied Sciences > Engineering >

High-speed computational ghost imaging with compressed sensing based on a convolutional neural network

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 7 pages

Abstract: Computational ghost imaging (CGI) has recently been intensively studied as anindirect imaging technique. However, the speed of CGI cannot meet therequirements of practical applications. Here, we propose a novel CGI scheme forhigh-speed imaging. In our scenario, the conventional CGI data processingalgorithm is optimized to a new compressed sensing (CS) algorithm based on aconvolutional neural network (CNN). CS is used to process the data collected bya conventional CGI device. Then, the processed data are trained by a CNN toreconstruct the image. The experimental results show that our scheme canproduce high-quality images with much less sampling than conventional CGI.Moreover, detailed comparisons between the images reconstructed using ourapproach and with conventional CS and deep learning (DL) show that our schemeoutperforms the conventional approach and achieves a faster imaging speed.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×