“Feature extraction” from digital images is an area of concern from few decades and Multiscale morphological operators is considered as successful approach for image processing and feature extraction applications. Although morphological operators is successful in solving the feature extraction but it too has some drawbacks. In this paper we model a non linear regularization method based on multi scale morphology for edge preserving super resolution (SR) image reconstruction. We formulate SR reconstruction problem from low resolution (LR) image as a deblurring and denoising and then solve the inverse problem using Bregman iterations. The proposed Method can be reduce inherent noise generated during low-resolution image formation as well as during SR image estimation efficiently. In our Simulation results show the effectiveness of the proposed method and reconstruction method for SR image.