Skip to main navigation Skip to search Skip to main content

Edge Aware Adaptive Filtering Method for Image Denoising

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper presents an adaptive edge-preserving image denoising technique. The proposed approach adaptively adjusts the filtering mask size and mask content to perform image denoising. The mask size is determined depending on the distance from the nearest edge in the image. Different edge detectors (Prewitt, Sobel, Canny, Perona-Malik) were considered and validated. The filtering mask coefficients were selected using various kernels, such as mean and median. The filtering quality of the proposed solution in its several variants was compared with anisotropic diffusion and frequently used spatial filtering techniques like mean or median that operate globally. The qualitative and quantitative comparison of the proposed method is based on commonly known image quality measures as well as on edge preservation measures. The obtained results show the potential of the method: Quality Index up to 0.84 and edge preservation β measure up to 98.49%.

Original languageEnglish
Title of host publicationProceedings of 25th International Conference Mixed Design of Integrated Circuits and Systems, MIXDES 2018
EditorsAndrzej Napieralski
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages371-375
Number of pages5
ISBN (Print)9788363578138
DOIs
Publication statusPublished - 14 Aug 2018
Event25th International Conference "Mixed Design of Integrated Circuits and Systems", MIXDES 2018 - Gdynia, Poland
Duration: 21 Jun 201823 Jun 2018

Publication series

NameProceedings of 25th International Conference Mixed Design of Integrated Circuits and Systems, MIXDES 2018

Conference

Conference25th International Conference "Mixed Design of Integrated Circuits and Systems", MIXDES 2018
Country/TerritoryPoland
CityGdynia
Period21/06/1823/06/18

Keywords

  • Perona-Malik
  • adaptive filtering
  • edge preserving
  • image denoising
  • image processing
  • spatial filtering

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Instrumentation

Fingerprint

Dive into the research topics of 'Edge Aware Adaptive Filtering Method for Image Denoising'. Together they form a unique fingerprint.

Cite this