Abstract :
Ubiquitous image blur brings out a practically important question - what are effective features to differentiate between blurred and unblurred image regions. We address it by studying a few blur feature representations in image gradient, Fourier domain, and data-driven local filters. Unlike previous methods, which are often based on restoration mechanisms, our features are constructed to enhance discriminative power and are adaptive to various blur scales in images. To avail evaluation, we build a new blur perception dataset containing thousands of images with labeled ground-truth. Our results are applied to several applications, including blur region segmentation, deblurring, and blur magnification.
Keywords :
Fourier analysis; filtering theory; image enhancement; image restoration; image segmentation; Fourier domain; blur feature representations; blur magnification; blur perception dataset; blur region segmentation; data-driven local filters; discriminative blur detection features; discriminative power enhancement; image deblurring; image gradient; labeled ground-truth; ubiquitous image blur; Deconvolution; Discrete Fourier transforms; Feature extraction; Image restoration; Kernel; Visualization; Image blur analysis; blur detection; blur feature;
