Comparative analysis of stomatal pore instance segmentation: Mask R-CNN vs. YOLOv8 on Phenomics Stomatal dataset

This study conducts a rigorous comparative analysis between two cutting-edge instance segmentation methods, Mask R-CNN and YOLOv8, focusing on stomata pore analysis. A novel dataset specifically tailored for stomata pore instance segmentation, named PhenomicsStomata, was introduced. This dataset pos...

Full description

Saved in:
Bibliographic Details
Main Authors: Thanh Tuan Thai, Ki-Bon Ku, Anh Tuan Le, San Su Min Oh, Ngo Hoang Phan, In-Jung Kim, Yong Suk Chung
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-12-01
Series:Frontiers in Plant Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpls.2024.1414849/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850174580897873920
author Thanh Tuan Thai
Thanh Tuan Thai
Thanh Tuan Thai
Ki-Bon Ku
Anh Tuan Le
Anh Tuan Le
San Su Min Oh
Ngo Hoang Phan
Ngo Hoang Phan
In-Jung Kim
Yong Suk Chung
Yong Suk Chung
author_facet Thanh Tuan Thai
Thanh Tuan Thai
Thanh Tuan Thai
Ki-Bon Ku
Anh Tuan Le
Anh Tuan Le
San Su Min Oh
Ngo Hoang Phan
Ngo Hoang Phan
In-Jung Kim
Yong Suk Chung
Yong Suk Chung
author_sort Thanh Tuan Thai
collection DOAJ
description This study conducts a rigorous comparative analysis between two cutting-edge instance segmentation methods, Mask R-CNN and YOLOv8, focusing on stomata pore analysis. A novel dataset specifically tailored for stomata pore instance segmentation, named PhenomicsStomata, was introduced. This dataset posed challenges such as low resolution and image imperfections, prompting the application of advanced preprocessing techniques, including image enhancement using the Lucy-Richardson Algorithm. The models underwent comprehensive evaluation, considering accuracy, precision, and recall as key parameters. Notably, YOLOv8 demonstrated superior performance over Mask R-CNN, particularly in accurately calculating stomata pore dimensions. Beyond this comparative study, the implications of our findings extend across diverse biological research, providing a robust foundation for advancing our understanding of plant physiology. Furthermore, the preprocessing enhancements offer valuable insights for refining image analysis techniques, showcasing the potential for broader applications in scientific domains. This research marks a significant stride in unraveling the complexities of plant structures, offering both theoretical insights and practical applications in scientific research.
format Article
id doaj-art-90f2bd42a36d46bb99bcdb806605d114
institution OA Journals
issn 1664-462X
language English
publishDate 2024-12-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Plant Science
spelling doaj-art-90f2bd42a36d46bb99bcdb806605d1142025-08-20T02:19:38ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2024-12-011510.3389/fpls.2024.14148491414849Comparative analysis of stomatal pore instance segmentation: Mask R-CNN vs. YOLOv8 on Phenomics Stomatal datasetThanh Tuan Thai0Thanh Tuan Thai1Thanh Tuan Thai2Ki-Bon Ku3Anh Tuan Le4Anh Tuan Le5San Su Min Oh6Ngo Hoang Phan7Ngo Hoang Phan8In-Jung Kim9Yong Suk Chung10Yong Suk Chung11Department of Plant Resources and Environment, Jeju National University, Jeju, Republic of KoreaMultimedia Communications Laboratory, University of Information Technology, Ho Chi Minh City, VietnamMultimedia Communications Laboratory, Vietnam National University, Ho Chi Minh City, VietnamDepartment of Electrical and Computer Engineering, Iowa State University, Ames, IA, United StatesMultimedia Communications Laboratory, Vietnam National University, Ho Chi Minh City, VietnamFaculty of Biology and Biotechnology, University of Science, Ho Chi Minh City, VietnamDepartment of Horticulture, Jeju National University, Jeju, Republic of KoreaMultimedia Communications Laboratory, Vietnam National University, Ho Chi Minh City, VietnamFaculty of Biology and Biotechnology, University of Science, Ho Chi Minh City, VietnamFaculty of Biotechnology, Bio-Resources Computing Research Center, Jeju National University, Jeju, Republic of KoreaDepartment of Plant Resources and Environment, Jeju National University, Jeju, Republic of KoreaPhytomix Corporation, Jeju, Republic of KoreaThis study conducts a rigorous comparative analysis between two cutting-edge instance segmentation methods, Mask R-CNN and YOLOv8, focusing on stomata pore analysis. A novel dataset specifically tailored for stomata pore instance segmentation, named PhenomicsStomata, was introduced. This dataset posed challenges such as low resolution and image imperfections, prompting the application of advanced preprocessing techniques, including image enhancement using the Lucy-Richardson Algorithm. The models underwent comprehensive evaluation, considering accuracy, precision, and recall as key parameters. Notably, YOLOv8 demonstrated superior performance over Mask R-CNN, particularly in accurately calculating stomata pore dimensions. Beyond this comparative study, the implications of our findings extend across diverse biological research, providing a robust foundation for advancing our understanding of plant physiology. Furthermore, the preprocessing enhancements offer valuable insights for refining image analysis techniques, showcasing the potential for broader applications in scientific domains. This research marks a significant stride in unraveling the complexities of plant structures, offering both theoretical insights and practical applications in scientific research.https://www.frontiersin.org/articles/10.3389/fpls.2024.1414849/fullstomataphenotypinginstance segmentationMask-RCNNYOLO
spellingShingle Thanh Tuan Thai
Thanh Tuan Thai
Thanh Tuan Thai
Ki-Bon Ku
Anh Tuan Le
Anh Tuan Le
San Su Min Oh
Ngo Hoang Phan
Ngo Hoang Phan
In-Jung Kim
Yong Suk Chung
Yong Suk Chung
Comparative analysis of stomatal pore instance segmentation: Mask R-CNN vs. YOLOv8 on Phenomics Stomatal dataset
Frontiers in Plant Science
stomata
phenotyping
instance segmentation
Mask-RCNN
YOLO
title Comparative analysis of stomatal pore instance segmentation: Mask R-CNN vs. YOLOv8 on Phenomics Stomatal dataset
title_full Comparative analysis of stomatal pore instance segmentation: Mask R-CNN vs. YOLOv8 on Phenomics Stomatal dataset
title_fullStr Comparative analysis of stomatal pore instance segmentation: Mask R-CNN vs. YOLOv8 on Phenomics Stomatal dataset
title_full_unstemmed Comparative analysis of stomatal pore instance segmentation: Mask R-CNN vs. YOLOv8 on Phenomics Stomatal dataset
title_short Comparative analysis of stomatal pore instance segmentation: Mask R-CNN vs. YOLOv8 on Phenomics Stomatal dataset
title_sort comparative analysis of stomatal pore instance segmentation mask r cnn vs yolov8 on phenomics stomatal dataset
topic stomata
phenotyping
instance segmentation
Mask-RCNN
YOLO
url https://www.frontiersin.org/articles/10.3389/fpls.2024.1414849/full
work_keys_str_mv AT thanhtuanthai comparativeanalysisofstomatalporeinstancesegmentationmaskrcnnvsyolov8onphenomicsstomataldataset
AT thanhtuanthai comparativeanalysisofstomatalporeinstancesegmentationmaskrcnnvsyolov8onphenomicsstomataldataset
AT thanhtuanthai comparativeanalysisofstomatalporeinstancesegmentationmaskrcnnvsyolov8onphenomicsstomataldataset
AT kibonku comparativeanalysisofstomatalporeinstancesegmentationmaskrcnnvsyolov8onphenomicsstomataldataset
AT anhtuanle comparativeanalysisofstomatalporeinstancesegmentationmaskrcnnvsyolov8onphenomicsstomataldataset
AT anhtuanle comparativeanalysisofstomatalporeinstancesegmentationmaskrcnnvsyolov8onphenomicsstomataldataset
AT sansuminoh comparativeanalysisofstomatalporeinstancesegmentationmaskrcnnvsyolov8onphenomicsstomataldataset
AT ngohoangphan comparativeanalysisofstomatalporeinstancesegmentationmaskrcnnvsyolov8onphenomicsstomataldataset
AT ngohoangphan comparativeanalysisofstomatalporeinstancesegmentationmaskrcnnvsyolov8onphenomicsstomataldataset
AT injungkim comparativeanalysisofstomatalporeinstancesegmentationmaskrcnnvsyolov8onphenomicsstomataldataset
AT yongsukchung comparativeanalysisofstomatalporeinstancesegmentationmaskrcnnvsyolov8onphenomicsstomataldataset
AT yongsukchung comparativeanalysisofstomatalporeinstancesegmentationmaskrcnnvsyolov8onphenomicsstomataldataset