Image deblurring using projective geometry and natural image statistics

摘要

The camera motion during image capturing results in poor and spoiled images. The conventional available methods to remove the camera shake assumes uniform spatial blur on the image, which in most of the cases is not a true assumption. Most of the available methods model the blur image as a convolution of sharp image and a blurring kernel, these results in more number of unknown parameters than known parameters. We propose a projective geometry non-uniform image deblurring model to handle the spatial non-uniformity in the blurred image. We also consider the results of research done in natural image statistics in our prior assumptions of blurring kernel and sharp image to increase the number of known parameters. We present a fully automated GUI based algorithm to make the application user friendly.