Machine Learning Methods for Automatic Segmentation of Images of Field- and Glasshouse-Based Plants for High-Throughput Phenotyping
Image segmentation is a fundamental but critical step for achieving automated high- throughput phenotyping. While conventional segmentation methods perform well in homogenous environments, the performance decreases when used in more complex environments. This study aimed to develop a fast and robust...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Plants |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2223-7747/12/10/2035 |
| _version_ | 1797598536349515776 |
|---|---|
| author | Frank Gyan Okyere Daniel Cudjoe Pouria Sadeghi-Tehran Nicolas Virlet Andrew B. Riche March Castle Latifa Greche Fady Mohareb Daniel Simms Manal Mhada Malcolm John Hawkesford |
| author_facet | Frank Gyan Okyere Daniel Cudjoe Pouria Sadeghi-Tehran Nicolas Virlet Andrew B. Riche March Castle Latifa Greche Fady Mohareb Daniel Simms Manal Mhada Malcolm John Hawkesford |
| author_sort | Frank Gyan Okyere |
| collection | DOAJ |
| description | Image segmentation is a fundamental but critical step for achieving automated high- throughput phenotyping. While conventional segmentation methods perform well in homogenous environments, the performance decreases when used in more complex environments. This study aimed to develop a fast and robust neural-network-based segmentation tool to phenotype plants in both field and glasshouse environments in a high-throughput manner. Digital images of cowpea (from glasshouse) and wheat (from field) with different nutrient supplies across their full growth cycle were acquired. Image patches from 20 randomly selected images from the acquired dataset were transformed from their original RGB format to multiple color spaces. The pixels in the patches were annotated as foreground and background with a pixel having a feature vector of 24 color properties. A feature selection technique was applied to choose the sensitive features, which were used to train a multilayer perceptron network (MLP) and two other traditional machine learning models: support vector machines (SVMs) and random forest (RF). The performance of these models, together with two standard color-index segmentation techniques (excess green (ExG) and excess green–red (ExGR)), was compared. The proposed method outperformed the other methods in producing quality segmented images with over 98%-pixel classification accuracy. Regression models developed from the different segmentation methods to predict Soil Plant Analysis Development (SPAD) values of cowpea and wheat showed that images from the proposed MLP method produced models with high predictive power and accuracy comparably. This method will be an essential tool for the development of a data analysis pipeline for high-throughput plant phenotyping. The proposed technique is capable of learning from different environmental conditions, with a high level of robustness. |
| first_indexed | 2024-03-11T03:23:31Z |
| format | Article |
| id | doaj.art-8978905b5f7f4babbf4cae606176a408 |
| institution | Directory Open Access Journal |
| issn | 2223-7747 |
| language | English |
| last_indexed | 2024-03-11T03:23:31Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Plants |
| spelling | doaj.art-8978905b5f7f4babbf4cae606176a4082023-11-18T02:56:42ZengMDPI AGPlants2223-77472023-05-011210203510.3390/plants12102035Machine Learning Methods for Automatic Segmentation of Images of Field- and Glasshouse-Based Plants for High-Throughput PhenotypingFrank Gyan Okyere0Daniel Cudjoe1Pouria Sadeghi-Tehran2Nicolas Virlet3Andrew B. Riche4March Castle5Latifa Greche6Fady Mohareb7Daniel Simms8Manal Mhada9Malcolm John Hawkesford10Sustainable Soils and Crops, Rothamsted Research, Harpenden AL5 2JQ, UKSustainable Soils and Crops, Rothamsted Research, Harpenden AL5 2JQ, UKSustainable Soils and Crops, Rothamsted Research, Harpenden AL5 2JQ, UKSustainable Soils and Crops, Rothamsted Research, Harpenden AL5 2JQ, UKSustainable Soils and Crops, Rothamsted Research, Harpenden AL5 2JQ, UKSustainable Soils and Crops, Rothamsted Research, Harpenden AL5 2JQ, UKSustainable Soils and Crops, Rothamsted Research, Harpenden AL5 2JQ, UKSchool of Water, Energy and Environment, Soil, Agrifood and Biosciences, Cranfield University, Bedford MK43 0AL, UKSchool of Water, Energy and Environment, Soil, Agrifood and Biosciences, Cranfield University, Bedford MK43 0AL, UKAfrican Integrated Plant and Soil Science, Agro-Biosciences, University of Mohammed VI Polytechnic, Lot 660, Ben Guerir 43150, MoroccoSustainable Soils and Crops, Rothamsted Research, Harpenden AL5 2JQ, UKImage segmentation is a fundamental but critical step for achieving automated high- throughput phenotyping. While conventional segmentation methods perform well in homogenous environments, the performance decreases when used in more complex environments. This study aimed to develop a fast and robust neural-network-based segmentation tool to phenotype plants in both field and glasshouse environments in a high-throughput manner. Digital images of cowpea (from glasshouse) and wheat (from field) with different nutrient supplies across their full growth cycle were acquired. Image patches from 20 randomly selected images from the acquired dataset were transformed from their original RGB format to multiple color spaces. The pixels in the patches were annotated as foreground and background with a pixel having a feature vector of 24 color properties. A feature selection technique was applied to choose the sensitive features, which were used to train a multilayer perceptron network (MLP) and two other traditional machine learning models: support vector machines (SVMs) and random forest (RF). The performance of these models, together with two standard color-index segmentation techniques (excess green (ExG) and excess green–red (ExGR)), was compared. The proposed method outperformed the other methods in producing quality segmented images with over 98%-pixel classification accuracy. Regression models developed from the different segmentation methods to predict Soil Plant Analysis Development (SPAD) values of cowpea and wheat showed that images from the proposed MLP method produced models with high predictive power and accuracy comparably. This method will be an essential tool for the development of a data analysis pipeline for high-throughput plant phenotyping. The proposed technique is capable of learning from different environmental conditions, with a high level of robustness.https://www.mdpi.com/2223-7747/12/10/2035feature extractionimagingmachine learningphenotypingsegmentation |
| spellingShingle | Frank Gyan Okyere Daniel Cudjoe Pouria Sadeghi-Tehran Nicolas Virlet Andrew B. Riche March Castle Latifa Greche Fady Mohareb Daniel Simms Manal Mhada Malcolm John Hawkesford Machine Learning Methods for Automatic Segmentation of Images of Field- and Glasshouse-Based Plants for High-Throughput Phenotyping Plants feature extraction imaging machine learning phenotyping segmentation |
| title | Machine Learning Methods for Automatic Segmentation of Images of Field- and Glasshouse-Based Plants for High-Throughput Phenotyping |
| title_full | Machine Learning Methods for Automatic Segmentation of Images of Field- and Glasshouse-Based Plants for High-Throughput Phenotyping |
| title_fullStr | Machine Learning Methods for Automatic Segmentation of Images of Field- and Glasshouse-Based Plants for High-Throughput Phenotyping |
| title_full_unstemmed | Machine Learning Methods for Automatic Segmentation of Images of Field- and Glasshouse-Based Plants for High-Throughput Phenotyping |
| title_short | Machine Learning Methods for Automatic Segmentation of Images of Field- and Glasshouse-Based Plants for High-Throughput Phenotyping |
| title_sort | machine learning methods for automatic segmentation of images of field and glasshouse based plants for high throughput phenotyping |
| topic | feature extraction imaging machine learning phenotyping segmentation |
| url | https://www.mdpi.com/2223-7747/12/10/2035 |
| work_keys_str_mv | AT frankgyanokyere machinelearningmethodsforautomaticsegmentationofimagesoffieldandglasshousebasedplantsforhighthroughputphenotyping AT danielcudjoe machinelearningmethodsforautomaticsegmentationofimagesoffieldandglasshousebasedplantsforhighthroughputphenotyping AT pouriasadeghitehran machinelearningmethodsforautomaticsegmentationofimagesoffieldandglasshousebasedplantsforhighthroughputphenotyping AT nicolasvirlet machinelearningmethodsforautomaticsegmentationofimagesoffieldandglasshousebasedplantsforhighthroughputphenotyping AT andrewbriche machinelearningmethodsforautomaticsegmentationofimagesoffieldandglasshousebasedplantsforhighthroughputphenotyping AT marchcastle machinelearningmethodsforautomaticsegmentationofimagesoffieldandglasshousebasedplantsforhighthroughputphenotyping AT latifagreche machinelearningmethodsforautomaticsegmentationofimagesoffieldandglasshousebasedplantsforhighthroughputphenotyping AT fadymohareb machinelearningmethodsforautomaticsegmentationofimagesoffieldandglasshousebasedplantsforhighthroughputphenotyping AT danielsimms machinelearningmethodsforautomaticsegmentationofimagesoffieldandglasshousebasedplantsforhighthroughputphenotyping AT manalmhada machinelearningmethodsforautomaticsegmentationofimagesoffieldandglasshousebasedplantsforhighthroughputphenotyping AT malcolmjohnhawkesford machinelearningmethodsforautomaticsegmentationofimagesoffieldandglasshousebasedplantsforhighthroughputphenotyping |