An enhanced classification of bacteria pathogen on microscopy images using deep learning

Classification of bacteria pathogens has significant importance issues in the clinical microbiology field. The taxonomy identification of bacteria is usually recognized through microscopy imaging. The classical procedure has the lacks detection and a high misclassification rate. Recently, computer-a...

Full description

Bibliographic Details
Main Authors: Son Ali, Akbar, Kamarul Hawari, Ghazali, Habsah, Hasan, Zeehaida, Mohamed, Wahyu Sapto, Aji
Format: Conference or Workshop Item
Language:English
English
Published: IEEE 2021
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/37877/
http://umpir.ump.edu.my/id/eprint/37877/1/An%20enhanced%20classification%20of%20bacteria%20pathogen%20on%20microscopy%20images_FULL.pdf
http://umpir.ump.edu.my/id/eprint/37877/2/An%20enhanced%20classification%20of%20bacteria%20pathogen%20on%20microscopy%20images%20.pdf
_version_ 1848825369402015744
author Son Ali, Akbar
Kamarul Hawari, Ghazali
Habsah, Hasan
Zeehaida, Mohamed
Wahyu Sapto, Aji
author_facet Son Ali, Akbar
Kamarul Hawari, Ghazali
Habsah, Hasan
Zeehaida, Mohamed
Wahyu Sapto, Aji
author_sort Son Ali, Akbar
building UMP Institutional Repository
collection Online Access
description Classification of bacteria pathogens has significant importance issues in the clinical microbiology field. The taxonomy identification of bacteria is usually recognized through microscopy imaging. The classical procedure has the lacks detection and a high misclassification rate. Recently, computer-aided detection is an applied deep learning approach that has been growing to improve classification quality. This study proposed an enhanced classification technique to recognize the bacterial pathogen images. The DensNet201 pre-trained CNN architecture has been used for deep feature extraction and classification. In addition, the transfer learning with the freeze layer technique applied can enhance the accuracy performance and reduce the false-positive rate. The experimental result can improve state-of-the-art decision-making.
first_indexed 2025-11-15T03:27:50Z
format Conference or Workshop Item
id ump-37877
institution Universiti Malaysia Pahang
institution_category Local University
language English
English
last_indexed 2025-11-15T03:27:50Z
publishDate 2021
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling ump-378772023-06-27T03:40:16Z http://umpir.ump.edu.my/id/eprint/37877/ An enhanced classification of bacteria pathogen on microscopy images using deep learning Son Ali, Akbar Kamarul Hawari, Ghazali Habsah, Hasan Zeehaida, Mohamed Wahyu Sapto, Aji QH Natural history RB Pathology TK Electrical engineering. Electronics Nuclear engineering Classification of bacteria pathogens has significant importance issues in the clinical microbiology field. The taxonomy identification of bacteria is usually recognized through microscopy imaging. The classical procedure has the lacks detection and a high misclassification rate. Recently, computer-aided detection is an applied deep learning approach that has been growing to improve classification quality. This study proposed an enhanced classification technique to recognize the bacterial pathogen images. The DensNet201 pre-trained CNN architecture has been used for deep feature extraction and classification. In addition, the transfer learning with the freeze layer technique applied can enhance the accuracy performance and reduce the false-positive rate. The experimental result can improve state-of-the-art decision-making. IEEE 2021 Conference or Workshop Item PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/37877/1/An%20enhanced%20classification%20of%20bacteria%20pathogen%20on%20microscopy%20images_FULL.pdf pdf en http://umpir.ump.edu.my/id/eprint/37877/2/An%20enhanced%20classification%20of%20bacteria%20pathogen%20on%20microscopy%20images%20.pdf Son Ali, Akbar and Kamarul Hawari, Ghazali and Habsah, Hasan and Zeehaida, Mohamed and Wahyu Sapto, Aji (2021) An enhanced classification of bacteria pathogen on microscopy images using deep learning. In: 4th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2021 , 16 December 2021 , Virtual, Yogyakarta. 119 -123.. ISBN 978-166540151-7 (Published) https://doi.org/10.1109/ISRITI54043.2021.9702809
spellingShingle QH Natural history
RB Pathology
TK Electrical engineering. Electronics Nuclear engineering
Son Ali, Akbar
Kamarul Hawari, Ghazali
Habsah, Hasan
Zeehaida, Mohamed
Wahyu Sapto, Aji
An enhanced classification of bacteria pathogen on microscopy images using deep learning
title An enhanced classification of bacteria pathogen on microscopy images using deep learning
title_full An enhanced classification of bacteria pathogen on microscopy images using deep learning
title_fullStr An enhanced classification of bacteria pathogen on microscopy images using deep learning
title_full_unstemmed An enhanced classification of bacteria pathogen on microscopy images using deep learning
title_short An enhanced classification of bacteria pathogen on microscopy images using deep learning
title_sort enhanced classification of bacteria pathogen on microscopy images using deep learning
topic QH Natural history
RB Pathology
TK Electrical engineering. Electronics Nuclear engineering
url http://umpir.ump.edu.my/id/eprint/37877/
http://umpir.ump.edu.my/id/eprint/37877/
http://umpir.ump.edu.my/id/eprint/37877/1/An%20enhanced%20classification%20of%20bacteria%20pathogen%20on%20microscopy%20images_FULL.pdf
http://umpir.ump.edu.my/id/eprint/37877/2/An%20enhanced%20classification%20of%20bacteria%20pathogen%20on%20microscopy%20images%20.pdf