Multi frame Super Resolution Reconstruction of Gray Scale Images

Multi frame image Super Resolution (SR) is a method which produces a high quality, high Resolution (HR) image from several noisy low resolution (LR) images of the same scene, acquired under different conditions. Super Resolution is a computationally intensive process. The purpose of this book is to develop a super resolution algorithm which can be applied to real time data and data generated synthetically. This book is categorized under two different frame works-an iterative approach and an interpolation and restoration approach. A fast and robust technique of multi frame super resolution reconstruction is presented where frame to frame motion estimation and image registration is developed iteratively using Lucas Kanade Pyramidal optical flow algorithm. A MATLAB based GUI for super resolution reconstructed image is developed which calculates the image quality parameters such as PSNR, RMSE, SD, SSIM and percentage change in pixels value in HR image with respect to original frame.

Autorentext

Dr.Netra Lokhande is currently working as an Associate Professor, in School of Electrical Engineering at MIT World Peace University, Pune (MITWPU). She works in the domain of Power Systems, Image Processing, Power Electronics and IOT.