Constrained Least Squares Filtering Team 15 R 95921037

Introduction – Inverse Filtering o Image Degradation n n o G(u, v) = H(u,

Improvement o Wiener Filtering K = Sn(u, v)/Sf(u, v), o Sn(u, v) = |N(u,

Improvement – Cons. o Constrained Least Squares Filtering o n P(u, v) is the

The Project o Implementation in Matlab n o Constrained Least Squares Filtering Collaborate with

Reference o o Andrews, H. C. , and Hunt, B. R. Digital Image Restoration,

Slides: 6

Download presentation

Constrained Least Squares Filtering Team 15 R 95921037 黃得源

Introduction – Inverse Filtering o Image Degradation n n o G(u, v) = H(u, v) F(u, v) = G(u, v)/H(u, v) Image Degradation with noise N(u, v)/H(u, v) could easily dominate the estimated image

Improvement o Wiener Filtering K = Sn(u, v)/Sf(u, v), o Sn(u, v) = |N(u, v)|2 o Sf(u, v) = |F(u, v)|2 Sn(u, v) & Sf(u, v) must be known o Sn(u, v) the power spectrum of the noise, o Sf(u, v) the power spectrum of the original image o n

Improvement – Cons. o Constrained Least Squares Filtering o n P(u, v) is the fourier transform of the Laplacian operator Constrain: o o |g – H |2 = |η|2 R(u, v) = G(u, v) – H(u, v) Adjust γfrom the constrain – by Newton-Raphson root-finding Apply algorithm from Prof. Hsien-Sen Hung(洪賢昇)

The Project o Implementation in Matlab n o Constrained Least Squares Filtering Collaborate with an other group n They would implement o o o n n Wiener Filter Inverse Filter Geometric Mean Filter Define Blur & Noise Function Compare the results of filters

Reference o o Andrews, H. C. , and Hunt, B. R. Digital Image Restoration, Prentice Hall, Englewood Cliffs, N. J. [1977]. Wiener, N. Extrapolation, Interpolation, and Smoothing of Stationary Time Series, the MIT Press, Cambridge, Mass. [1942]. R. Woods, R. Gonzalez, Digital Image Processing (2 nd Edition) M. Bilgen, H. S. Hung, Constrained least-squares filtering for noisy images blurred by random point spread function, Optical Engineering, June. 1994