Efficient Image Deblurring Application Using Combination of Blind Deconvolution Method and Blur Parameters Estimation Method

Abstract

Image deblurring can be formulated as the inverse process of image blurring. The degraded image can be improved and reconstructed to its original form using image deblurring. Image reconstruction in elementary mode begins with estimation of degradation parameters followed with application of some classical restoration approach. This paper introduces a new approach for image restoration. Here, removal of motion blurs is done through blind deconvolution technique. Two motion parameters angle (θ) and length have been considered for estimation. Hough transform method is used for estimation of blur parameters. PSNR and MSE are employed to exploit important image characteristics, such as denoising, error, randomness, etc. Proposed algorithm is tested for accuracy. Experiments are carried out to study important image features, which play a major role during image restoration.