• BALAKRISHNA MANDAL
• KHAGENDRA KUMAR
• YASH TEJWANI
• D. PUNITHA

The Super Resolute (SR) model enhances the quality of a low-resolution image to a high resolution. The quality of the output image will be significantly improved and contain more details. The existing system uses deep neural network to enhance the image quality by applying the little filters many times in deep network which help get more contextual information over the low resolute image. The proposed model uses CNN (Convolutional Neural Network) to extract features from the input image and Residual patch data will be calculated. The proposed architecture uses shallow Neural Network which significantly enhances the computational time. It will extracts more information using residual patch map data to restore lost image details. The proposed model is better than the existing CNN models in terms of accuracy and computational time and it is significantly faster than existing models in terms of batch processing.

Super-Resolution, Shallow Neural Network, Convolutional Neural Network

"Image Super-Resolution using Shallow Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 3, page no.445-449, March-2019, Available :http://www.jetir.org/papers/JETIR1903G63.pdf

"Image Super-Resolution using Shallow Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 3, page no. pp445-449, March-2019, Available at : http://www.jetir.org/papers/JETIR1903G63.pdf