An Improved Variational-Based Model for Denoising and Segmentation of Vector-Valued Images

Preserving important features such as edges is one of the main concerns in models for denoising and segmenting vector-valued (colour) images. The Rudin-Osher-Fatemi (ROF) model is a well-known variational-based image denoising model that is capable of reducing image noise while preserving image edge...

Full description

Bibliographic Details
Published in:Journal of Advanced Research in Applied Sciences and Engineering Technology
Main Author: Ismail N.; Jumaat A.K.; Zulkarnain N.F.A.
Format: Article
Language:English
Published: Semarak Ilmu Publishing 2024
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85185689936&doi=10.37934%2faraset.40.1.189203&partnerID=40&md5=54503ece340878bb7971f324d1d18dc3
id 2-s2.0-85185689936
spelling 2-s2.0-85185689936
Ismail N.; Jumaat A.K.; Zulkarnain N.F.A.
An Improved Variational-Based Model for Denoising and Segmentation of Vector-Valued Images
2024
Journal of Advanced Research in Applied Sciences and Engineering Technology
40
1
10.37934/araset.40.1.189203
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85185689936&doi=10.37934%2faraset.40.1.189203&partnerID=40&md5=54503ece340878bb7971f324d1d18dc3
Preserving important features such as edges is one of the main concerns in models for denoising and segmenting vector-valued (colour) images. The Rudin-Osher-Fatemi (ROF) model is a well-known variational-based image denoising model that is capable of reducing image noise while preserving image edges. However, the ROF model is not formulated for denoising colour images and is less effective in preserving corners and weak edges. On the other hand, a variational-based selective segmentation model for colour images called the selective distance segmentation (DSS2) model has recently been proposed, which can effectively partition or extract a specific object in an image. However, the DSS2 model has problems in segmenting colour images with noise, which may result in poor segmentation. Therefore, in this research, we first modify the ROF model to denoise vector-valued images by including the edge detector and extending the formulation into a vector-valued framework. Second, we reformulate the DSS2 model by incorporating the modified ROF model as a new fitting term in the DSS2 model. Peak signal-to-noise ratio (PSNR) is used to measure the image quality, while Jaccard and Dice similarity index are used to evaluate the segmentation quality. The comparison between our proposed model and existing model shows that our model is more effective as indicated by higher PSNR, Jaccard and Dice similarity index values. © 2024, Semarak Ilmu Publishing. All rights reserved.
Semarak Ilmu Publishing
24621943
English
Article
All Open Access; Hybrid Gold Open Access
author Ismail N.; Jumaat A.K.; Zulkarnain N.F.A.
spellingShingle Ismail N.; Jumaat A.K.; Zulkarnain N.F.A.
An Improved Variational-Based Model for Denoising and Segmentation of Vector-Valued Images
author_facet Ismail N.; Jumaat A.K.; Zulkarnain N.F.A.
author_sort Ismail N.; Jumaat A.K.; Zulkarnain N.F.A.
title An Improved Variational-Based Model for Denoising and Segmentation of Vector-Valued Images
title_short An Improved Variational-Based Model for Denoising and Segmentation of Vector-Valued Images
title_full An Improved Variational-Based Model for Denoising and Segmentation of Vector-Valued Images
title_fullStr An Improved Variational-Based Model for Denoising and Segmentation of Vector-Valued Images
title_full_unstemmed An Improved Variational-Based Model for Denoising and Segmentation of Vector-Valued Images
title_sort An Improved Variational-Based Model for Denoising and Segmentation of Vector-Valued Images
publishDate 2024
container_title Journal of Advanced Research in Applied Sciences and Engineering Technology
container_volume 40
container_issue 1
doi_str_mv 10.37934/araset.40.1.189203
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85185689936&doi=10.37934%2faraset.40.1.189203&partnerID=40&md5=54503ece340878bb7971f324d1d18dc3
description Preserving important features such as edges is one of the main concerns in models for denoising and segmenting vector-valued (colour) images. The Rudin-Osher-Fatemi (ROF) model is a well-known variational-based image denoising model that is capable of reducing image noise while preserving image edges. However, the ROF model is not formulated for denoising colour images and is less effective in preserving corners and weak edges. On the other hand, a variational-based selective segmentation model for colour images called the selective distance segmentation (DSS2) model has recently been proposed, which can effectively partition or extract a specific object in an image. However, the DSS2 model has problems in segmenting colour images with noise, which may result in poor segmentation. Therefore, in this research, we first modify the ROF model to denoise vector-valued images by including the edge detector and extending the formulation into a vector-valued framework. Second, we reformulate the DSS2 model by incorporating the modified ROF model as a new fitting term in the DSS2 model. Peak signal-to-noise ratio (PSNR) is used to measure the image quality, while Jaccard and Dice similarity index are used to evaluate the segmentation quality. The comparison between our proposed model and existing model shows that our model is more effective as indicated by higher PSNR, Jaccard and Dice similarity index values. © 2024, Semarak Ilmu Publishing. All rights reserved.
publisher Semarak Ilmu Publishing
issn 24621943
language English
format Article
accesstype All Open Access; Hybrid Gold Open Access
record_format scopus
collection Scopus
_version_ 1809677775442804736