This chapter presents the following content: Restoration techniques, inverse filtering, minimum mean square error (wiener), constrained least square filter, restoration in presence of periodic noise, estimation of degradation model, restoration techniques. | Digital Image Processing CSC331 Image restoration 1 Summery of previous lecture Estimation of Degradation Model By observation By experimentation Mathematical model Restoration techniques Inverse filtering 2 Todays lecture Restoration techniques Inverse filtering Minimum Mean Square error (Wiener) Constrained Least square Filter Restoration in presence of periodic noise 3 Degradation Model by observation 4 Example degraded image which has been cut out from a bigger degraded image. 5 Degradation Model by experimentation So, our requirement is that whichever imaging device or imaging setup that has been used for getting a degraded image which has been used to record a degraded image for experimentation purpose; then we try to find out that what is the impulse response of that imaging setup. As we have already discussed that it is the impulse response which completely characterizes any system. If we know what is the impulse response of the system; we can always calculate the response of the system to any type of input signal. We simulate an impulse by using a narrow strong beam of light. 6 Simulated impulse 7 simulated impulse Impulse response which is captured by the camera when this impulse falls on camera lens. Now, we know from our earlier discussion that for a narrow impulse, the Fourier transformation of an impulse is a constant. Degradation by Mathematical Model 8 Degradation by Mathematical Model 9 Motion blurring mathematical modeling 10 11 Inverse filtering Results 12 Inverse filtering results for motion blur 13 Motion blurring mathematical modeling 14 point spread function 15 direct inverse filtering Fourier transformation of the point spread function 16 degradation model was recomputed from Fourier transformation of the point spread function. minimum mean square error approach or Wiener filtering the Wiener filtering tries to reconstruct the degraded image by minimizing an error function. 17 18 19 Results with Wiener filter 20 Constant least square . | Digital Image Processing CSC331 Image restoration 1 Summery of previous lecture Estimation of Degradation Model By observation By experimentation Mathematical model Restoration techniques Inverse filtering 2 Todays lecture Restoration techniques Inverse filtering Minimum Mean Square error (Wiener) Constrained Least square Filter Restoration in presence of periodic noise 3 Degradation Model by observation 4 Example degraded image which has been cut out from a bigger degraded image. 5 Degradation Model by experimentation So, our requirement is that whichever imaging device or imaging setup that has been used for getting a degraded image which has been used to record a degraded image for experimentation purpose; then we try to find out that what is the impulse response of that imaging setup. As we have already discussed that it is the impulse response which completely characterizes any system. If we know what is the impulse response of the system; we can always calculate the response .
