The task of blind deblurring usually consists of
estimation of interim images and blur kernels. Due to the lack of information in kernels compared to that in interim images, when only a blurred image is available, most of deblurring methods emphasis the estimation of interim images. However, the resulting kernel is often wider than it should be, thus degrading the quality of the deconvolved image. To remedy the problem of wide kernels, we present a thinning scheme to better estimate a kernel. In this way, a
clear image can be recovered from a camera-shake blurred image. To mitigate the insufficient information of blur kernels, we make simple inferences and assumptions for kernels based on the trajectory of the camera shake. Under these inferences and assumptions, we use a three-step approach to estimate the blur kernel. Firstly, we relax the condition to find the shape of the blur kernel. Next, we use a thinning algorithm to obtain the skeleton of the blur
kernel. Thirdly, we reweight the blur kernel by Gaussian distribution. By repeating these steps a few times we can get a more accurate blur kernel. Finally, we can reconstruct a high quality deblurred image by using the blur kernel. The proposed method is tested by a public database and our results outperform those of two similar methods.
關聯:
Proceedings of the 6th IIAE International Conference on Intelligent Systems and Image Processing 2018
