Denoising Based Nonlinear Image Quality Enhancement on Digital Images
D. Ferlin Deva Shahila1, S. H. Krishnaveni2

1D. Ferlin Deva Shahila, Assistant Professor, Department of ECE, Loyola Institute of Technology and Science, Kanyakumari (Tamil Nadu), India.
2S. H. Krishnaveni, Associate Professor, Department of CSE, Baselios Mathews II College of Engineering, Kollam (Kerala), India.
Manuscript received on 26 May 2019 | Revised Manuscript received on 13 June 2019 | Manuscript Published on 26 June 2019 | PP: 333-339 | Volume-8 Issue-1S5 June 2019 | Retrieval Number: A00580681S519/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: The use of computer is more powerful in digital images (DI). Enhancement of image quality (IQ) and the sharpness are the linked tasks to be performed. Besides, the latest growth of data intensive multimedia based applications put many demands on researchers to discover usage of the images in the applications. Over the past years, various representation systems for quality assessment on DI governed by mathematical and algorithmic framework have been proposed. However, the most common shortcomings of these methods are the lack of non-linear denoising artifacts over multiple scales. To accomplish non-linear noise eradication on DI, a Denoising based Nonlinear image quality Enhancement (DNIQE) is developed. DNIQE framework lessens the noise artifacts to enhance IQ. In DNIQE k, Adaptive Structures Directional Lifting (ASDL) with Discrete Wavelet Transform (DWT) presents multi scale histogram representation on DI. ASDL modifies sampling matrix into sub-regions of DI and enhance the performance of lossy-to-lossless image coding application. A Sinc interpolation filter with constant coefficient is considered in ASDL scheme to interpolate both straight and perpendicular direction of DI to lessen prediction errors in coding results. At last, lossy and lossless DI coding results of DNIQE framework is shown to validate the advantages of proposed structure. The proposed framework is estimated using Manuscripts and Archives digital images Database (MADID). The result analysis shows the performance improvement in IQ by enhancing PSNR during coding results which lessens noising artifacts in extensive manner.
Keywords: Multimedia, Non-linear Denoising, Artifacts, Directional Lifting, Discrete Wavelet Transform, Sinc Interpolation Filter.
Scope of the Article: Digital System and Logic Design