F. Kara and C. Vural (Turkey)
Image processing, blind image super-resolution, 2-d constant modulus algorithm
A blind image resolution enhancement method based on complex representation of images and complex filtering is proposed. It is based on a 2-d constant modulus algorithm and it is for pure translational motion only. It drastically increases the performance of our previously proposed method which was based on real filtering and which gave poor results for eight-bit images. Some important properties of out method are that it does not assume the availability of blur parameters, the blur functions don’t need to be the same for the low-resolution images, and also they don’t need to be shift-invariant.
Important Links:
Go Back
