Image deblurring using saliency detection

Motion deblurring is a vastly used technique in image processing and is an interesting task in this field. In this paper an algorithm is proposed for the detection of saliency to create boundaries of the object under observation. In the next step segmentation of the image is performed to separate the image from the background. The image is uniformly blurred by performing kernel estimation of the background image and convoluting it with the focused part of the image. Finally deconvolution is performed on the image in order to obtain a clear image.