Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2018 Apr 27;13(4):e0196615.
doi: 10.1371/journal.pone.0196615. eCollection 2018.

An automated, high-throughput plant phenotyping system using machine learning-based plant segmentation and image analysis

Unseok Lee  1 , Sungyul Chang  1 , Gian Anantrio Putra  1 , Hyoungseok Kim  1 , Dong Hwan Kim  2
Affiliations

An automated, high-throughput plant phenotyping system using machine learning-based plant segmentation and image analysis

Unseok Lee et al. PLoS One. .

Abstract

A high-throughput plant phenotyping system automatically observes and grows many plant samples. Many plant sample images are acquired by the system to determine the characteristics of the plants (populations). Stable image acquisition and processing is very important to accurately determine the characteristics. However, hardware for acquiring plant images rapidly and stably, while minimizing plant stress, is lacking. Moreover, most software cannot adequately handle large-scale plant imaging. To address these problems, we developed a new, automated, high-throughput plant phenotyping system using simple and robust hardware, and an automated plant-imaging-analysis pipeline consisting of machine-learning-based plant segmentation. Our hardware acquires images reliably and quickly and minimizes plant stress. Furthermore, the images are processed automatically. In particular, large-scale plant-image datasets can be segmented precisely using a classifier developed using a superpixel-based machine-learning algorithm (Random Forest), and variations in plant parameters (such as area) over time can be assessed using the segmented images. We performed comparative evaluations to identify an appropriate learning algorithm for our proposed system, and tested three robust learning algorithms. We developed not only an automatic analysis pipeline but also a convenient means of plant-growth analysis that provides a learning data interface and visualization of plant growth trends. Thus, our system allows end-users such as plant biologists to analyze plant growth via large-scale plant image data easily.

PubMed Disclaimer

Conflict of interest statement

Competing Interests: The authors have declared that no competing interests exist.

Figures

Fig 1
Fig 1. The pipeline of the plant phenotyping system.
Fig 2
Fig 2. The hardware setup.
A: System layout. B: The plant-phenotyping room. C,D: System configuration; the robotic arm moves the module from tray to tray and acquires top-view images.
Fig 3
Fig 3. Top-view images.
A: Top-view original tray images using color marker detection. B: The warped image based on the color markers.
Fig 4
Fig 4. Top-view images.
A: Estimation of tray edge coordinates. B: A cropped single-pot image.
Fig 5
Fig 5. Top view of a tray showing pot labeling.
Fig 6
Fig 6. Superpixel images.
Fig 7
Fig 7. Plant-growth visualization; tracking plant area over time.
Fig 8
Fig 8. The ground-truth image-creation user interface.
Fig 9
Fig 9. A validation dataset (left) and a test dataset (right).
Fig 10
Fig 10. The F1 scores of the three classifiers.
A: F1 scores of validation data sets. B: F1 scores of test data sets.
Fig 11
Fig 11. Segmentation results after post-processing using three trained classifiers (Original, SVM, MLP, and RF).
Fig 12
Fig 12. Precision-recall curves of the three classifiers.
A: Precision-recall curves of validation data sets. B: Precision-recall curves of test data sets.
Fig 13
Fig 13. Plant-growth analysis; tracking plant area over time.
See this image and copyright information in PMC

References

    1. Chen D, Neumann K, Friedel S, Kilian B, Chen M, Altmann T, et al. Dissecting the Phenotypic Components of Crop Plant Growth and Drought Responses Based on High-Throughput Image Analysis. The Plant Cell Online. 2014;26(December):4636–4655. doi: 10.1105/tpc.114.129601 - DOI - PMC - PubMed
    1. Crimmins MA, Crimmins ÆTM. Monitoring Plant Phenology Using Digital Repeat Photography. Environmental Management. 2008;41(February):949–958. doi: 10.1007/s00267-008-9086-6 - DOI - PubMed
    1. Berger B, de Regt B, Tester M. High-Throughput Phenotyping of Plant Shoots; 2012. p. 9–20. Available from: http://link.springer.com/10.1007/978-1-61779-995-2_2. - DOI - PubMed
    1. Leister D, Varotto C, Pesaresi P, Niwergall A, Salamini F. Large-scale evaluation of plant growth in Arabidopsis thaliana by non-invasive image analysis. Plant Physiology and Biochemistry. 1999;37(9):671–678. https://doi.org/10.1016/S0981-9428(00)80097-2. - DOI
    1. Cai J, Golzarian MR, Miklavcic SJ. Novel Image Segmentation Based on Machine Learning and Its Application to Plant Analysis. International Journal of Information and Electronics Engineering. 2011;1(1):79–84.

Publication types