PROJECT TITLE :

Edge-Based Defocus Blur Estimation With Adaptive Scale Selection - 2018

ABSTRACT:

Objects that do not lie at the focal distance of a digital camera generate defocused regions in the captured image. This Project presents a replacement edge-based method for spatially varying defocus blur estimation employing a single image based mostly on reblurred gradient magnitudes. The proposed approach initially computes a scale-consistent edge map of the input image and selects a native reblurring scale aiming to address noise, edge mis-localization, and interfering edges. An initial blur estimate is computed at the detected scale-consistent edge points and a completely unique connected edge filter is proposed to smooth the sparse blur map based on pixel connectivity among detected edge contours. Finally, a quick guided filter is employed to propagate the sparse blur map through the entire image. Experimental results show that the proposed approach presents a very smart compromise between estimation error and running time when compared with the state-of-the-art strategies. We tend to additionally explore our blur estimation methodology in the context of image deblurring, and show that metrics sometimes used to evaluate blur estimation could not correlate as expected with the visual quality of the deblurred image.