Cargando…
Improvement in the Between-Class Variance Based on Lognormal Distribution for Accurate Image Segmentation
There are various distributions of image histograms where regions form symmetrically or asymmetrically based on the frequency of the intensity levels inside the image. In pure image processing, the process of optimal thresholding tends to accurately separate each region in the image histogram to obt...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9497484/ https://www.ncbi.nlm.nih.gov/pubmed/36141093 http://dx.doi.org/10.3390/e24091204 |
_version_ | 1784794516699480064 |
---|---|
author | Jumiawi, Walaa Ali H. El-Zaart, Ali |
author_facet | Jumiawi, Walaa Ali H. El-Zaart, Ali |
author_sort | Jumiawi, Walaa Ali H. |
collection | PubMed |
description | There are various distributions of image histograms where regions form symmetrically or asymmetrically based on the frequency of the intensity levels inside the image. In pure image processing, the process of optimal thresholding tends to accurately separate each region in the image histogram to obtain the segmented image. Otsu’s method is the most used technique in image segmentation. Otsu algorithm performs automatic image thresholding and returns the optimal threshold by maximizing between-class variance using the sum of Gaussian distribution for the intensity level in the histogram. There are various types of images where an intensity level has right-skewed histograms and does not fit with the between-class variance of the original Otsu algorithm. In this paper, we proposed an improvement of the between-class variance based on lognormal distribution, using the mean and the variance of the lognormal. The proposed model aims to handle the drawbacks of asymmetric distribution, especially for images with right-skewed intensity levels. Several images were tested for segmentation in the proposed model in parallel with the original Otsu method and the relevant work, including simulated images and Medical Resonance Imaging (MRI) of brain tumors. Two types of evaluation measures were used in this work based on unsupervised and supervised metrics. The proposed model showed superior results, and the segmented images indicated better threshold estimation against the original Otsu method and the related improvement. |
format | Online Article Text |
id | pubmed-9497484 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-94974842022-09-23 Improvement in the Between-Class Variance Based on Lognormal Distribution for Accurate Image Segmentation Jumiawi, Walaa Ali H. El-Zaart, Ali Entropy (Basel) Article There are various distributions of image histograms where regions form symmetrically or asymmetrically based on the frequency of the intensity levels inside the image. In pure image processing, the process of optimal thresholding tends to accurately separate each region in the image histogram to obtain the segmented image. Otsu’s method is the most used technique in image segmentation. Otsu algorithm performs automatic image thresholding and returns the optimal threshold by maximizing between-class variance using the sum of Gaussian distribution for the intensity level in the histogram. There are various types of images where an intensity level has right-skewed histograms and does not fit with the between-class variance of the original Otsu algorithm. In this paper, we proposed an improvement of the between-class variance based on lognormal distribution, using the mean and the variance of the lognormal. The proposed model aims to handle the drawbacks of asymmetric distribution, especially for images with right-skewed intensity levels. Several images were tested for segmentation in the proposed model in parallel with the original Otsu method and the relevant work, including simulated images and Medical Resonance Imaging (MRI) of brain tumors. Two types of evaluation measures were used in this work based on unsupervised and supervised metrics. The proposed model showed superior results, and the segmented images indicated better threshold estimation against the original Otsu method and the related improvement. MDPI 2022-08-29 /pmc/articles/PMC9497484/ /pubmed/36141093 http://dx.doi.org/10.3390/e24091204 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Jumiawi, Walaa Ali H. El-Zaart, Ali Improvement in the Between-Class Variance Based on Lognormal Distribution for Accurate Image Segmentation |
title | Improvement in the Between-Class Variance Based on Lognormal Distribution for Accurate Image Segmentation |
title_full | Improvement in the Between-Class Variance Based on Lognormal Distribution for Accurate Image Segmentation |
title_fullStr | Improvement in the Between-Class Variance Based on Lognormal Distribution for Accurate Image Segmentation |
title_full_unstemmed | Improvement in the Between-Class Variance Based on Lognormal Distribution for Accurate Image Segmentation |
title_short | Improvement in the Between-Class Variance Based on Lognormal Distribution for Accurate Image Segmentation |
title_sort | improvement in the between-class variance based on lognormal distribution for accurate image segmentation |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9497484/ https://www.ncbi.nlm.nih.gov/pubmed/36141093 http://dx.doi.org/10.3390/e24091204 |
work_keys_str_mv | AT jumiawiwalaaalih improvementinthebetweenclassvariancebasedonlognormaldistributionforaccurateimagesegmentation AT elzaartali improvementinthebetweenclassvariancebasedonlognormaldistributionforaccurateimagesegmentation |