Advances in prokaryote classification from microscopic images

Great knowledge and experience on microbiology are required for accurate bacteria identification. Automation of bacteria identification is required because there might be a shortage of skilled microbiologists and clinicians at a time of great need. We propose an automatic bacteria identification fr...

Full description

Bibliographic Details
Main Authors: Mohamad , Amaleena, Jusoh, Noorain A., Htike@Muhammad Yusof, Zaw Zaw, Shoon , Lei Win
Format: Article
Language:English
Published: Wireilla Scientific Publications, Australia 2014
Subjects:
Online Access:http://irep.iium.edu.my/38594/
http://irep.iium.edu.my/38594/
http://irep.iium.edu.my/38594/
http://irep.iium.edu.my/38594/1/3214ecij02.pdf
id iium-38594
recordtype eprints
spelling iium-385942018-06-12T04:42:49Z http://irep.iium.edu.my/38594/ Advances in prokaryote classification from microscopic images Mohamad , Amaleena Jusoh, Noorain A. Htike@Muhammad Yusof, Zaw Zaw Shoon , Lei Win Q Science (General) Great knowledge and experience on microbiology are required for accurate bacteria identification. Automation of bacteria identification is required because there might be a shortage of skilled microbiologists and clinicians at a time of great need. We propose an automatic bacteria identification framework that can classify three famous classes of bacteria namely Cocci, Bacilli and Vibrio from microscopic morphology using the Naïve Bayes classifier. The proposed bacteria identification framework comprises two steps. In the first step, the system is trained using a set of microscopic images containing Cocci, Bacilli, and Vibrio. The input images are normalized to emphasize the diameter and shape features. Edge-based descriptors are then extracted from the input images. In the second step, we use the Naïve Bayes classifier to perform probabilistic inference based on the input descriptors. 64 images for each class of bacteria were used as the training set and 222 images consisting of the three classes of bacteria and other random images such as humans and airplanes were used as the test set. There are no images overlapped between the training set and the test set. The system was found to be able to accurately discriminate the three classes of bacteria. Moreover, the system was also found to be able to reject images that did not belong to any of the three classes of bacteria. The preliminary results demonstrate how a simple machine learning classifier with a set of simple image-based features can result in high classification accuracy. The preliminary results also demonstrate the efficacy and efficiency of our two-step automatic bacteria identification approach and motivate us to extend this framework to identify a variety of other types of bacteria. Wireilla Scientific Publications, Australia 2014-06 Article PeerReviewed application/pdf en http://irep.iium.edu.my/38594/1/3214ecij02.pdf Mohamad , Amaleena and Jusoh, Noorain A. and Htike@Muhammad Yusof, Zaw Zaw and Shoon , Lei Win (2014) Advances in prokaryote classification from microscopic images. Electrical & Computer Engineering: An International Journal (ECIJ), 3 (2). pp. 13-24. ISSN 2201-5957 http://wireilla.com/engg/ecij/current2014.html 10.14810/ecij.2014.3202
repository_type Digital Repository
institution_category Local University
institution International Islamic University Malaysia
building IIUM Repository
collection Online Access
language English
topic Q Science (General)
spellingShingle Q Science (General)
Mohamad , Amaleena
Jusoh, Noorain A.
Htike@Muhammad Yusof, Zaw Zaw
Shoon , Lei Win
Advances in prokaryote classification from microscopic images
description Great knowledge and experience on microbiology are required for accurate bacteria identification. Automation of bacteria identification is required because there might be a shortage of skilled microbiologists and clinicians at a time of great need. We propose an automatic bacteria identification framework that can classify three famous classes of bacteria namely Cocci, Bacilli and Vibrio from microscopic morphology using the Naïve Bayes classifier. The proposed bacteria identification framework comprises two steps. In the first step, the system is trained using a set of microscopic images containing Cocci, Bacilli, and Vibrio. The input images are normalized to emphasize the diameter and shape features. Edge-based descriptors are then extracted from the input images. In the second step, we use the Naïve Bayes classifier to perform probabilistic inference based on the input descriptors. 64 images for each class of bacteria were used as the training set and 222 images consisting of the three classes of bacteria and other random images such as humans and airplanes were used as the test set. There are no images overlapped between the training set and the test set. The system was found to be able to accurately discriminate the three classes of bacteria. Moreover, the system was also found to be able to reject images that did not belong to any of the three classes of bacteria. The preliminary results demonstrate how a simple machine learning classifier with a set of simple image-based features can result in high classification accuracy. The preliminary results also demonstrate the efficacy and efficiency of our two-step automatic bacteria identification approach and motivate us to extend this framework to identify a variety of other types of bacteria.
format Article
author Mohamad , Amaleena
Jusoh, Noorain A.
Htike@Muhammad Yusof, Zaw Zaw
Shoon , Lei Win
author_facet Mohamad , Amaleena
Jusoh, Noorain A.
Htike@Muhammad Yusof, Zaw Zaw
Shoon , Lei Win
author_sort Mohamad , Amaleena
title Advances in prokaryote classification from microscopic images
title_short Advances in prokaryote classification from microscopic images
title_full Advances in prokaryote classification from microscopic images
title_fullStr Advances in prokaryote classification from microscopic images
title_full_unstemmed Advances in prokaryote classification from microscopic images
title_sort advances in prokaryote classification from microscopic images
publisher Wireilla Scientific Publications, Australia
publishDate 2014
url http://irep.iium.edu.my/38594/
http://irep.iium.edu.my/38594/
http://irep.iium.edu.my/38594/
http://irep.iium.edu.my/38594/1/3214ecij02.pdf
first_indexed 2023-09-18T20:55:26Z
last_indexed 2023-09-18T20:55:26Z
_version_ 1777410272679428096