• NAGOTHI MOULIKA

Image reconstruction is challenging now-a-days due to the ill-poseness of the inverse problem and very few number of detected photons. As of late profound deep neural networks have been widely and effectively utilized in PC vision errands and attracted in developing areas like medical imaging, astronomy and many more. In this work, we trained a deep residual convolutional neural network to improve image quality by using the existing training datasets information. We form the target work as an constrained enhancement problem and solve it using the convolutional neural network (CNN) algorithm. The trained datasets are used to evaluate the proposed method. The primary point of Image depixelizer is to change over the given low-resolution image into respective high and super-resolution image. Experimental results shows that the embedded Image depixelizer is quite robust in face of various low-resolution images and provides good results in terms of resolution

Image Depixelizer, Convolutional neural network (CNN), Residual Neural Network (ResNET), Enhanced Deep Residual Network for Single Image Super-Resolution.

"Image Depixelizer Using Enhanced Deep Residual Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 10, page no.b342-b345, October-2021, Available :http://www.jetir.org/papers/JETIR2110136.pdf

"Image Depixelizer Using Enhanced Deep Residual Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 10, page no. ppb342-b345, October-2021, Available at : http://www.jetir.org/papers/JETIR2110136.pdf