Web-SpikeSegNet: Deep Learning Framework for Recognition and Counting of Spikes From Visual Images of Wheat Plants

Computer vision with deep learning is emerging as a significant approach for non-invasive and non-destructive plant phenotyping. Spikes are the reproductive organs of wheat plants. Detection and counting of spikes considered the grain-bearing organ have great importance in the phenomics study of lar...

Full description

Saved in:
Bibliographic Details
Main Authors: Tanuj Misra, Alka Arora, Sudeep Marwaha, Ranjeet Ranjan Jha, Mrinmoy Ray, Rajni Jain, A. R. Rao, Eldho Varghese, Shailendra Kumar, Sudhir Kumar, Aditya Nigam, Rabi Narayan Sahoo, Viswanathan Chinnusamy
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9432817/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849223139793305600
author Tanuj Misra
Alka Arora
Sudeep Marwaha
Ranjeet Ranjan Jha
Mrinmoy Ray
Rajni Jain
A. R. Rao
Eldho Varghese
Shailendra Kumar
Sudhir Kumar
Aditya Nigam
Rabi Narayan Sahoo
Viswanathan Chinnusamy
author_facet Tanuj Misra
Alka Arora
Sudeep Marwaha
Ranjeet Ranjan Jha
Mrinmoy Ray
Rajni Jain
A. R. Rao
Eldho Varghese
Shailendra Kumar
Sudhir Kumar
Aditya Nigam
Rabi Narayan Sahoo
Viswanathan Chinnusamy
author_sort Tanuj Misra
collection DOAJ
description Computer vision with deep learning is emerging as a significant approach for non-invasive and non-destructive plant phenotyping. Spikes are the reproductive organs of wheat plants. Detection and counting of spikes considered the grain-bearing organ have great importance in the phenomics study of large sets of germplasms. In the present study, we developed an online platform, &#x201C;Web-SpikeSegNet,&#x201D; based on a deep-learning framework for spike detection and counting from the wheat plant&#x2019;s visual images. The architecture of the Web-SpikeSegNet consists of 2 layers. First Layer, Client-Side Interface Layer, deals with end user&#x2019;s requests and corresponding responses management. In contrast, the second layer, Server Side Application Layer, consists of a spike detection and counting module. The backbone of the spike detection module comprises of deep encoder-decoder network with hourglass network for spike segmentation. The Spike counting module implements the &#x201C;Analyze Particle&#x201D; function of imageJ to count the number of spikes. For evaluating the performance of Web-SpikeSegNet, we acquired the wheat plant&#x2019;s visual images, and the satisfactory segmentation performances were obtained as Type I error 0.00159, Type II error 0.0586, Accuracy 99.65&#x0025;, Precision 99.59&#x0025; and F<sub>1</sub> score 99.65&#x0025;. As spike detection and counting in wheat phenotyping are closely related to the yield, Web-SpikeSegNet is a significant step forward in the field of wheat phenotyping and will be very useful to the researchers and students working in the domain.
format Article
id doaj-art-d1936b60753a4ef59eab2ac0f25c6365
institution Kabale University
issn 2169-3536
language English
publishDate 2021-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-d1936b60753a4ef59eab2ac0f25c63652025-08-25T23:00:50ZengIEEEIEEE Access2169-35362021-01-019762357624710.1109/ACCESS.2021.30808369432817Web-SpikeSegNet: Deep Learning Framework for Recognition and Counting of Spikes From Visual Images of Wheat PlantsTanuj Misra0Alka Arora1https://orcid.org/0000-0003-0999-1077Sudeep Marwaha2Ranjeet Ranjan Jha3Mrinmoy Ray4Rajni Jain5https://orcid.org/0000-0002-8493-7858A. R. Rao6Eldho Varghese7Shailendra Kumar8Sudhir Kumar9https://orcid.org/0000-0002-1089-7435Aditya Nigam10https://orcid.org/0000-0003-4755-0619Rabi Narayan Sahoo11Viswanathan Chinnusamy12ICAR-Indian Agricultural Statistics Research Institute, New Delhi, IndiaICAR-Indian Agricultural Statistics Research Institute, New Delhi, IndiaICAR-Indian Agricultural Statistics Research Institute, New Delhi, IndiaSchool of Computing and Electrical Engineering (SCEE), IIT Mandi, Mandi, IndiaICAR-Indian Agricultural Statistics Research Institute, New Delhi, IndiaICAR&#x2014;National Institute of Agricultural Economics and Policy Research (NIAP), New Delhi, IndiaICAR-Indian Agricultural Statistics Research Institute, New Delhi, IndiaICAR-Central Marine Fisheries Research Institute, Kochi, IndiaDepartment of Computer Science, Rani Lakshmi Bai Central Agricultural University, Jhansi, IndiaICAR-Indian Agricultural Research Institute, Library Avenue, New Delhi, IndiaSchool of Computing and Electrical Engineering (SCEE), IIT Mandi, Mandi, IndiaICAR-Indian Agricultural Research Institute, Library Avenue, New Delhi, IndiaICAR-Indian Agricultural Research Institute, Library Avenue, New Delhi, IndiaComputer vision with deep learning is emerging as a significant approach for non-invasive and non-destructive plant phenotyping. Spikes are the reproductive organs of wheat plants. Detection and counting of spikes considered the grain-bearing organ have great importance in the phenomics study of large sets of germplasms. In the present study, we developed an online platform, &#x201C;Web-SpikeSegNet,&#x201D; based on a deep-learning framework for spike detection and counting from the wheat plant&#x2019;s visual images. The architecture of the Web-SpikeSegNet consists of 2 layers. First Layer, Client-Side Interface Layer, deals with end user&#x2019;s requests and corresponding responses management. In contrast, the second layer, Server Side Application Layer, consists of a spike detection and counting module. The backbone of the spike detection module comprises of deep encoder-decoder network with hourglass network for spike segmentation. The Spike counting module implements the &#x201C;Analyze Particle&#x201D; function of imageJ to count the number of spikes. For evaluating the performance of Web-SpikeSegNet, we acquired the wheat plant&#x2019;s visual images, and the satisfactory segmentation performances were obtained as Type I error 0.00159, Type II error 0.0586, Accuracy 99.65&#x0025;, Precision 99.59&#x0025; and F<sub>1</sub> score 99.65&#x0025;. As spike detection and counting in wheat phenotyping are closely related to the yield, Web-SpikeSegNet is a significant step forward in the field of wheat phenotyping and will be very useful to the researchers and students working in the domain.https://ieeexplore.ieee.org/document/9432817/Computer visiondeep learningdeep encoder-decoderhourglassimage analysisspike detection and counting
spellingShingle Tanuj Misra
Alka Arora
Sudeep Marwaha
Ranjeet Ranjan Jha
Mrinmoy Ray
Rajni Jain
A. R. Rao
Eldho Varghese
Shailendra Kumar
Sudhir Kumar
Aditya Nigam
Rabi Narayan Sahoo
Viswanathan Chinnusamy
Web-SpikeSegNet: Deep Learning Framework for Recognition and Counting of Spikes From Visual Images of Wheat Plants
IEEE Access
Computer vision
deep learning
deep encoder-decoder
hourglass
image analysis
spike detection and counting
title Web-SpikeSegNet: Deep Learning Framework for Recognition and Counting of Spikes From Visual Images of Wheat Plants
title_full Web-SpikeSegNet: Deep Learning Framework for Recognition and Counting of Spikes From Visual Images of Wheat Plants
title_fullStr Web-SpikeSegNet: Deep Learning Framework for Recognition and Counting of Spikes From Visual Images of Wheat Plants
title_full_unstemmed Web-SpikeSegNet: Deep Learning Framework for Recognition and Counting of Spikes From Visual Images of Wheat Plants
title_short Web-SpikeSegNet: Deep Learning Framework for Recognition and Counting of Spikes From Visual Images of Wheat Plants
title_sort web spikesegnet deep learning framework for recognition and counting of spikes from visual images of wheat plants
topic Computer vision
deep learning
deep encoder-decoder
hourglass
image analysis
spike detection and counting
url https://ieeexplore.ieee.org/document/9432817/
work_keys_str_mv AT tanujmisra webspikesegnetdeeplearningframeworkforrecognitionandcountingofspikesfromvisualimagesofwheatplants
AT alkaarora webspikesegnetdeeplearningframeworkforrecognitionandcountingofspikesfromvisualimagesofwheatplants
AT sudeepmarwaha webspikesegnetdeeplearningframeworkforrecognitionandcountingofspikesfromvisualimagesofwheatplants
AT ranjeetranjanjha webspikesegnetdeeplearningframeworkforrecognitionandcountingofspikesfromvisualimagesofwheatplants
AT mrinmoyray webspikesegnetdeeplearningframeworkforrecognitionandcountingofspikesfromvisualimagesofwheatplants
AT rajnijain webspikesegnetdeeplearningframeworkforrecognitionandcountingofspikesfromvisualimagesofwheatplants
AT arrao webspikesegnetdeeplearningframeworkforrecognitionandcountingofspikesfromvisualimagesofwheatplants
AT eldhovarghese webspikesegnetdeeplearningframeworkforrecognitionandcountingofspikesfromvisualimagesofwheatplants
AT shailendrakumar webspikesegnetdeeplearningframeworkforrecognitionandcountingofspikesfromvisualimagesofwheatplants
AT sudhirkumar webspikesegnetdeeplearningframeworkforrecognitionandcountingofspikesfromvisualimagesofwheatplants
AT adityanigam webspikesegnetdeeplearningframeworkforrecognitionandcountingofspikesfromvisualimagesofwheatplants
AT rabinarayansahoo webspikesegnetdeeplearningframeworkforrecognitionandcountingofspikesfromvisualimagesofwheatplants
AT viswanathanchinnusamy webspikesegnetdeeplearningframeworkforrecognitionandcountingofspikesfromvisualimagesofwheatplants