Image Denoising Method Based On Curvelet Transform with Thresholding Functions

NEEMA . N; Dr.M.Sasikumar

CALL FOR PAPERS : Dec-2023

Submission Last Date

25-Dec-23

Submit Manuscript Online

FOR AUTHORS

FOR REVIEWERS

ARCHIEVES

DOWNLOADS

Open Access

Image Denoising Method Based On Curvelet Transform with Thresholding Functions

Author(s):

NEEMA . N , MARIAN ENGINEERING COLLEGE ,TRIVANDRUM; Dr.M.Sasikumar, Marian Engineering College

Keywords:

Curvelets, Discrete Wavelet Transform (DWT), Fast Discrete Curvelet Transform (FDCT) Filtering, Radon Transform, Ridgelets, Thresholding Rules, Wavelets

Abstract:

Visual information which is transmitted in the form of digital images is becoming a major method of communication now a day. But the main drawback in digital images is the presence of noise while their acquisition or transmission. Removing noise from digital images is a challenge for researchers. Several noise removal algorithms have been proposed till date. Choice of any denoising algorithm is application dependent and it depends upon the type of noise present in the image. Every denoising method has its own assumptions, advantages and limitations. In this paper a new image denoising method which is based on Curvelet transform is proposed. The limitations of commonly used separable extensions of one-dimensional transforms, such as the Fourier transform and wavelet transforms, in capturing the geometry of image edges are well known. Here we pursue "true" two dimensional transform, Curvelet Transform that can capture the intrinsic geometrical structure that is very important in visual information. Denoising of an image is done by Curvelet Transform with a thresholding function and the results are compared with different denoising methods. The Proposed method has the advantage of achieving a good visual quality of images while preserving the curved edges of an image. The proposed method is applied to different images such as grayscale image, color image, microscopic image, and seismic image. Experimental results show that proposed denoising technique performs better than other methods in terms of the PSNR.