Dynamic Convolutional Neural Network For Image Super-resolution
DOI:
https://doi.org/10.3126/jacem.v3i0.18808Keywords:
Super-resolution, Convolutional Neural Network, Dynamic convolutional neural networkAbstract
Single image super-resolution (SISR) is a technique that reconstructs high resolution image from single low resolution image. Dynamic Convolutional Neural Network (DCNN) is used here for the reconstruction of high resolution image from single low resolution image. It takes low resolution image as input and produce high resolution image as output for dynamic up-scaling factor 2, 3, and 4. The dynamic convolutional neural network directly learns an end-to-end mapping between low resolution and high resolution images. The CNN trained simultaneously with images up-scaled by factors 2, 3, and 4 to make it dynamic. The system is then tested for the input images with up-scaling factors 2, 3 and 4. The dynamically trained CNN performs well for all three up-scaling factors. The performance of network is measured by PSNR, WPSNR, SSIM, MSSSIM, and also by perceptual.
Journal of Advanced College of Engineering and Management, Vol. 3, 2017, Page: 1-10
Downloads
Downloads
Published
How to Cite
Issue
Section
License
JACEM reserves the copyright for the published papers. Author will have right to use content of the published paper in part or in full for their own work.