Identifier

etd-05132009-120913

Degree

Master of Science in Electrical Engineering (MSEE)

Department

Electrical and Computer Engineering

Document Type

Thesis

Abstract

The bilateral filter is a nonlinear filter that does spatial averaging without smoothing edges. It has shown to be an effective image denoising technique. It also can be applied to the blocking artifacts reduction. An important issue with the application of the bilateral filter is the selection of the filter parameters, which affect the results significantly. Another research interest of bilateral filter is acceleration of the computation speed. There are three main contributions of this thesis. The first contribution is an empirical study of the optimal bilateral filter parameter selection in image denoising. I propose an extension of the bilateral filter: multi resolution bilateral filter, where bilateral filtering is applied to the low-frequency sub-bands of a signal decomposed using a wavelet filter bank. The multi resolution bilateral filter is combined with wavelet thresholding to form a new image denoising framework, which turns out to be very effective in eliminating noise in real noisy images. The second contribution is that I present a spatially adaptive method to reduce compression artifacts. To avoid over-smoothing texture regions and to effectively eliminate blocking and ringing artifacts, in this paper, texture regions and block boundary discontinuities are first detected; these are then used to control/adapt the spatial and intensity parameters of the bilateral filter. The test results prove that the adaptive method can improve the quality of restored images significantly better than the standard bilateral filter. The third contribution is the improvement of the fast bilateral filter, in which I use a combination of multi windows to approximate the Gaussian filter more precisely.

Date

2009

Document Availability at the Time of Submission

Release the entire work immediately for access worldwide.

Committee Chair

Gunturk, Bahadir

DOI

10.31390/gradschool_theses.1912

Download

Share

COinS