Abstract
Images are very good information carriers but they depart from their original condition during transmission and are corrupted by different kind of noise. The purpose is to remove the noisy coefficients such that minimum amount of information is lost and maximum amount of noise is suppressed or reduced. We considered Generalized Gaussian distribution for modeling of noise. In the proposed technique, statistical thresholding methods are used for the estimation of threshold value while Bi-orthogonal wavelet has been envisaged for image decomposition and reconstruction. A qualitative and quantitative analysis of thresholding methods on different images shows significant results for statistical thresholding methods based on objective and subjective quality as compared to other de-noising methods.
Highlights
In the era of this digital world the use of digital images is greatly increased
In [1] spatial domain filtering is used for the purpose of de-noising and in [2] transformed domain is used for image de-noising which shows improved results than spatial domain filtering
We applied bi orthogonal 6.8 (Bior6.8) wavelet and decomposition level five in our simulations.to check the performance we compared the results with hard thresholding, soft thresholding, visu shrink, statistical method 1 and statistical method 2 using Peak signal to noise ratio (PSNR)[16]
Summary
In the era of this digital world the use of digital images is greatly increased. Digital images are used in satellite, medical, radar, computer vision and pattern recognition. In 1995, Dohono and Johnstone invented a method of wavelet shrinkage which shows good results for 1-D signal de-noising and inverse problem solving [3]. These methods failed to meet improve the removal of noise from images. By using statistical thresholding methods for de-noising and compression using two dimensional (2-D) discrete wavelet transform (DWT). In order to remove the noise and to retain the important features wavelet thresholding method and scale de-noising method is used for image de-noising and compression. We have used bi-orthogonal 6.8 wavelet family which shows improved results, high de-noising, compression and edge preserving.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: International Journal of Advanced Computer Science and Applications
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.