Towards Automated Analysis of Grain Spikes in Greenhouse Images Using Neural Network Approaches: A Comparative Investigation of Six Methods
Automated analysis of small and optically variable plant organs, such as grain spikes, is highly demanded in quantitative plant science and breeding. Previous works primarily focused on the detection of prominently visible spikes emerging on the top of the grain plants growing in field conditions. H...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/22/7441 |
| _version_ | 1827675444024967168 |
|---|---|
| author | Sajid Ullah Michael Henke Narendra Narisetti Klára Panzarová Martin Trtílek Jan Hejatko Evgeny Gladilin |
| author_facet | Sajid Ullah Michael Henke Narendra Narisetti Klára Panzarová Martin Trtílek Jan Hejatko Evgeny Gladilin |
| author_sort | Sajid Ullah |
| collection | DOAJ |
| description | Automated analysis of small and optically variable plant organs, such as grain spikes, is highly demanded in quantitative plant science and breeding. Previous works primarily focused on the detection of prominently visible spikes emerging on the top of the grain plants growing in field conditions. However, accurate and automated analysis of all fully and partially visible spikes in greenhouse images renders a more challenging task, which was rarely addressed in the past. A particular difficulty for image analysis is represented by leaf-covered, occluded but also matured spikes of bushy crop cultivars that can hardly be differentiated from the remaining plant biomass. To address the challenge of automated analysis of arbitrary spike phenotypes in different grain crops and optical setups, here, we performed a comparative investigation of six neural network methods for pattern detection and segmentation in RGB images, including five deep and one shallow neural network. Our experimental results demonstrate that advanced deep learning methods show superior performance, achieving over 90% accuracy by detection and segmentation of spikes in wheat, barley and rye images. However, spike detection in new crop phenotypes can be performed more accurately than segmentation. Furthermore, the detection and segmentation of matured, partially visible and occluded spikes, for which phenotypes substantially deviate from the training set of regular spikes, still represent a challenge to neural network models trained on a limited set of a few hundreds of manually labeled ground truth images. Limitations and further potential improvements of the presented algorithmic frameworks for spike image analysis are discussed. Besides theoretical and experimental investigations, we provide a GUI-based tool (SpikeApp), which shows the application of pre-trained neural networks to fully automate spike detection, segmentation and phenotyping in images of greenhouse-grown plants. |
| first_indexed | 2024-03-10T05:05:05Z |
| format | Article |
| id | doaj.art-809f54c958a54ad19a00344090331f23 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T05:05:05Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-809f54c958a54ad19a00344090331f232023-11-23T01:23:15ZengMDPI AGSensors1424-82202021-11-012122744110.3390/s21227441Towards Automated Analysis of Grain Spikes in Greenhouse Images Using Neural Network Approaches: A Comparative Investigation of Six MethodsSajid Ullah0Michael Henke1Narendra Narisetti2Klára Panzarová3Martin Trtílek4Jan Hejatko5Evgeny Gladilin6Plant Sciences Core Facility, CEITEC—Central European Institute of Technology, Masaryk University, 60200 Brno, Czech RepublicPlant Sciences Core Facility, CEITEC—Central European Institute of Technology, Masaryk University, 60200 Brno, Czech RepublicLeibniz Institute of Plant Genetics and Crop Plant Research (IPK), 06466 Gatersleben, GermanyPSI (Photon Systems Instruments), spol. s r.o., 66424 Drasov, Czech RepublicPSI (Photon Systems Instruments), spol. s r.o., 66424 Drasov, Czech RepublicPlant Sciences Core Facility, CEITEC—Central European Institute of Technology, Masaryk University, 60200 Brno, Czech RepublicLeibniz Institute of Plant Genetics and Crop Plant Research (IPK), 06466 Gatersleben, GermanyAutomated analysis of small and optically variable plant organs, such as grain spikes, is highly demanded in quantitative plant science and breeding. Previous works primarily focused on the detection of prominently visible spikes emerging on the top of the grain plants growing in field conditions. However, accurate and automated analysis of all fully and partially visible spikes in greenhouse images renders a more challenging task, which was rarely addressed in the past. A particular difficulty for image analysis is represented by leaf-covered, occluded but also matured spikes of bushy crop cultivars that can hardly be differentiated from the remaining plant biomass. To address the challenge of automated analysis of arbitrary spike phenotypes in different grain crops and optical setups, here, we performed a comparative investigation of six neural network methods for pattern detection and segmentation in RGB images, including five deep and one shallow neural network. Our experimental results demonstrate that advanced deep learning methods show superior performance, achieving over 90% accuracy by detection and segmentation of spikes in wheat, barley and rye images. However, spike detection in new crop phenotypes can be performed more accurately than segmentation. Furthermore, the detection and segmentation of matured, partially visible and occluded spikes, for which phenotypes substantially deviate from the training set of regular spikes, still represent a challenge to neural network models trained on a limited set of a few hundreds of manually labeled ground truth images. Limitations and further potential improvements of the presented algorithmic frameworks for spike image analysis are discussed. Besides theoretical and experimental investigations, we provide a GUI-based tool (SpikeApp), which shows the application of pre-trained neural networks to fully automate spike detection, segmentation and phenotyping in images of greenhouse-grown plants.https://www.mdpi.com/1424-8220/21/22/7441high-throughput plant image analysisspike detectionspike segmentationdeep learningautomated plant phenotyping |
| spellingShingle | Sajid Ullah Michael Henke Narendra Narisetti Klára Panzarová Martin Trtílek Jan Hejatko Evgeny Gladilin Towards Automated Analysis of Grain Spikes in Greenhouse Images Using Neural Network Approaches: A Comparative Investigation of Six Methods Sensors high-throughput plant image analysis spike detection spike segmentation deep learning automated plant phenotyping |
| title | Towards Automated Analysis of Grain Spikes in Greenhouse Images Using Neural Network Approaches: A Comparative Investigation of Six Methods |
| title_full | Towards Automated Analysis of Grain Spikes in Greenhouse Images Using Neural Network Approaches: A Comparative Investigation of Six Methods |
| title_fullStr | Towards Automated Analysis of Grain Spikes in Greenhouse Images Using Neural Network Approaches: A Comparative Investigation of Six Methods |
| title_full_unstemmed | Towards Automated Analysis of Grain Spikes in Greenhouse Images Using Neural Network Approaches: A Comparative Investigation of Six Methods |
| title_short | Towards Automated Analysis of Grain Spikes in Greenhouse Images Using Neural Network Approaches: A Comparative Investigation of Six Methods |
| title_sort | towards automated analysis of grain spikes in greenhouse images using neural network approaches a comparative investigation of six methods |
| topic | high-throughput plant image analysis spike detection spike segmentation deep learning automated plant phenotyping |
| url | https://www.mdpi.com/1424-8220/21/22/7441 |
| work_keys_str_mv | AT sajidullah towardsautomatedanalysisofgrainspikesingreenhouseimagesusingneuralnetworkapproachesacomparativeinvestigationofsixmethods AT michaelhenke towardsautomatedanalysisofgrainspikesingreenhouseimagesusingneuralnetworkapproachesacomparativeinvestigationofsixmethods AT narendranarisetti towardsautomatedanalysisofgrainspikesingreenhouseimagesusingneuralnetworkapproachesacomparativeinvestigationofsixmethods AT klarapanzarova towardsautomatedanalysisofgrainspikesingreenhouseimagesusingneuralnetworkapproachesacomparativeinvestigationofsixmethods AT martintrtilek towardsautomatedanalysisofgrainspikesingreenhouseimagesusingneuralnetworkapproachesacomparativeinvestigationofsixmethods AT janhejatko towardsautomatedanalysisofgrainspikesingreenhouseimagesusingneuralnetworkapproachesacomparativeinvestigationofsixmethods AT evgenygladilin towardsautomatedanalysisofgrainspikesingreenhouseimagesusingneuralnetworkapproachesacomparativeinvestigationofsixmethods |