Vincent DeVito Computer Systems Lab 2009-2010 Image Deblurring Vincent DeVito Computer Systems Lab 2009-2010
Abstract The goal of my project is to take an image input, artificially blur it using a known blur kernel, then using deconvolution techniques to deblur and restore the image, then run a last step to reduce the noise of the image. The goal is to have the input and output images be identical with a blurry intermediate image.
Abstract Condensed
Background Running goal for image processors and photo editors Many methods of deconvolution exist Many utilize the Fourier Transform Current progress focused on blur kernel estimation Better kernel more accurate, clear output image
Related Projects The group of Lu Yuan, et al. designed project with blurry/noisy image pairs Blurry image intensity + noisy image sharpness + deconvolution = sharp, deblurred output image The group of Rob Fergus, et al. designed project to estimate blur kernel from naturally blurred image A few inputs + kernel estimation algorithm + deconvolution = deblurred output image with few artifacts
Application Photography Improve image quality Restore image
Application (Cont.) Machine Vision Requires input images to be of good clarity Blur could ruin techniques such as edge detection Intermediate step
Current Work Basic image processing techniques (HIPR2 online worksheets) Pointwise operations, geometric operations, morphology
Expected Results First version Clear input artificial blurring using known blur kernel deconvolution techniques using same kernel reduce noise output image Hope to have the output image be as clear and sharp as the original input image
Expected Results (Cont.) Final Version (hopefully) Naturally blurred input estimation of unknown blur kernel deconvolution techniques using that kernel reduce noise output image Hope to have the output image be a clear, sharp version of the blurry input image