A joint estimation approach for two-tone image deblurring by blind deconvolution
Tóm tắt
A new statistical method is proposed for deblurring two-tone images, i.e., images with two unknown grey levels, that are blurred by an unknown linear filter. The key idea of the proposed method is to adjust a deblurring filter until its output becomes two tone. Two optimization criteria are proposed for the adjustment of the deblurring filter. A three-step iterative algorithm (TSIA) is also proposed to minimize the criteria. It is proven mathematically that by minimizing either of the criteria, the original (nonblurred) image, along with the blur filter, will be recovered uniquely (only with possible scale/shift ambiguities) at high SNR. The recovery is guaranteed not only for i.i.d. images but also for correlated and nonstationary images. It does not require a priori knowledge of the statistical parameters or the tone values of the original image; neither does it require a priori knowledge of the phase or other special information (e.g., FIR, symmetry, nonnegativity, etc.) about the blur filter. Numerical experiments are carried out to test the method on synthetic and real images.
Từ khóa
#Image restoration #Deconvolution #Finite impulse response filter #Nonlinear filters #Degradation #Cameras #Statistics #Information filtering #Information filters #Statistical analysisTài liệu tham khảo
10.1109/78.80914
10.1111/j.1467-9892.1993.tb00167.x
10.1109/83.502395
ortega, 1970, Iterative Solution of Nonlinear Equations in Several Variables
10.1109/97.704975
10.1007/978-1-4615-3980-3
combettes, 1989, methods for digital restoration of signals degraded by a stochastic impulse response, IEEE Trans on Acoustics Speech and Signal Processing, 37, 393, 10.1109/29.21706
10.1109/29.17544
10.1109/83.403444
10.1109/79.489268
haykin, 1994, Blind Deconvolution
10.1109/78.80894
10.1109/29.57545
10.1109/TASSP.1986.1164886
mesarović, 2000, iterative linear minimum mean-square-error image restoration for partially known blur, J Opt Soc Amer, 17, 711, 10.1364/JOSAA.17.000711
10.1364/JOSAA.9.001508
10.1214/aos/1176324542
10.1109/ICPR.1992.202049
10.1109/IVS.1995.528287
10.1109/18.108246
10.1109/5.53403
li, 1996, multichannel blind deconvolution when input signals have discrete alphabets, Proc 30th Conf Inform Sci Syst, 885
andrews, 1977, Digital Image Restoration
10.1049/el:19900765
10.1109/83.217225
10.1109/18.669282
10.1016/1049-9652(91)90025-F
10.1109/2.153254
10.1080/09500349214551141
10.1364/JOSAA.11.002401
10.1109/78.655423
10.1214/aos/1176345984
10.1109/83.491316
10.1016/B978-0-12-256420-8.50024-1
10.1109/PROC.1981.12022