• A Deepika
• Dr S. Jhansi Rani

Image registration plays an important role in many practical problems in diverse fields such as medical, remote sensing, and computer vision. The basic purpose of image registration is to obtain the finest geometrical and radiometrically aligned image from temporal or multi-modal image sensors. In this project, a novel stable shape feature-based image registration method has been proposed by matching the stable region with a set of rotations, scale invariant features, and multi-scale image segmentation is used to obtain the matching areas. Noise present in the image gives adverse effect to the image, hence denoise is performed using CNN. The removal of noise provide adequate and accuracy for various range of applications. The PSNR values will be calculated. The Experiment results are obtained using Matlab software tool.

image registration, multi-scale image segmentation, De-noising, Convolutional Neural Networks

"DENOISING OF AUTOMATIC IMAGE REGISTRATION USING CONVOLUTIONAL NEURAL NETWOEK", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.664-669, June 2019, Available :http://www.jetir.org/papers/JETIR1907H97.pdf

"DENOISING OF AUTOMATIC IMAGE REGISTRATION USING CONVOLUTIONAL NEURAL NETWOEK", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp664-669, June 2019, Available at : http://www.jetir.org/papers/JETIR1907H97.pdf