|International Journal of Computer Applications
|Foundation of Computer Science (FCS), NY, USA
|Volume 43 - Number 20
|Year of Publication: 2012
|Authors: L. Jimson, P. Senthil, D. Chandrakanth
L. Jimson, P. Senthil, D. Chandrakanth . A New Methodology for Blind Image Deconvolution. International Journal of Computer Applications. 43, 20 ( April 2012), 1-5. DOI=10.5120/6216-8686
In image processing, the elimination of noise is a highly difficult in research area. It is one of the most important powerful technologies that will form science and engineering in the twenty first century. The broad knowledge, digital image processing is any shape of information processing used for which both input and output are images, such as photographs. Image restoration method is mainly used to eliminate the inescapable distortions and noise that leave into an image at some point in the image capture process. Direct image restoration difficulty is briefly revisited subsequently a recent method based on inverse filtering for the perfect image restoration in noiseless case is proposed. Noisy case is addressed by means of introducing a regularization term into the objective function in order to avoid the noise amplification. The filter recognition problem is considered in the Multichannel context. A new strong solution to estimate the degradation matrix filter is then derived and used in combination with a total variation approach to restore the original image.