deposit_your_work

A Wavelet-Based Statistical Model for Image Restoration

Files in this item

Files Size Format View
Wan2001Oct5AWavelet-B.PDF 95.94Kb application/pdf Thumbnail
Wan2001Oct5AWavelet-B.PS 984.1Kb application/postscript View/Open

Show full item record

Item Metadata

Title: A Wavelet-Based Statistical Model for Image Restoration
Author: Wan, Yi; Nowak, Robert David
Type: Conference paper
Keywords: wavelet; image restoration; MAP; Gaussian mixture; EM algorithm
Citation: Y. Wan and R. D. Nowak, "A Wavelet-Based Statistical Model for Image Restoration," 2001.
Abstract: In this paper we develop a wavelet-based statistical method for solving the image restoration problem. In this approach, a signal prior is set up by modeling the image wavelet coefficients as independent Gaussian mixture random variables. We first specify a uniform (non-informative) distribution on the mixing parameters, which leads to a simple and efficient iterative algorithm for MAP estimation. This algorithm is similar to the EM algorithm in that it alternates between a state estimation step and a maximization step. Moreover, we show that our algroithm converges monotonically to a local maximum of the posterior distribution. We next generalize the result to non-uniform priors and develop an efficient integer programming algorithm that enables a similar alternating optimization procedure.
Date Published: 2001-10-20

This item appears in the following Collection(s)

  • ECE Publications [1048 items]
    Publications by Rice University Electrical and Computer Engineering faculty and graduate students
  • DSP Publications [508 items]
    Publications by Rice Faculty and graduate students in digital signal processing.