A segmentation procedure using colour features applied to images of Arabidopsis thaliana

A two-step registration-classification approach to automated segmentation of multimodal images for high-throughput greenhouse plant phenotyping

BACKGROUND

Automated segmentation of large amount of image data is one of the major bottlenecks in high-throughput plant phenotyping. Dynamic optical appearance of developing plants, inhomogeneous scene illumination, shadows and reflections in plant and background regions complicate automated segmentation of unimodal plant images. To overcome the problem of ambiguous color information in unimodal data, images of different modalities can be combined to a virtual multispectral cube. However, due to motion artefacts caused by the relocation of plants between photochambers the alignment of multimodal images is often compromised by blurring artifacts.

RESULTS

Here, we present an approach to automated segmentation of greenhouse plant images which is based on co-registration of fluorescence (FLU) and of visible light (VIS) camera images followed by subsequent separation of plant and marginal background regions using different species- and camera view-tailored classification models. Our experimental results including a direct comparison with manually segmented ground truth data show that images of different plant types acquired at different developmental stages from different camera views can be automatically segmented with the average accuracy of 93 % ( S D = 5 % ) using our two-step registration-classification approach.

CONCLUSION

Automated segmentation of arbitrary greenhouse images exhibiting highly variable optical plant and background appearance represents a challenging task to data classification techniques that rely on detection of invariances. To overcome the limitation of unimodal image analysis, a two-step registration-classification approach to combined analysis of fluorescent and visible light images was developed. Our experimental results show that this algorithmic approach enables accurate segmentation of different FLU/VIS plant images suitable for application in fully automated high-throughput manner.

Arabidopsis phenotyping through geometric morphometrics

Background

Recently, great technical progress has been achieved in the field of plant phenotyping. High-throughput platforms and the development of improved algorithms for rosette image segmentation make it possible to extract shape and size parameters for genetic, physiological, and environmental studies on a large scale. The development of low-cost phenotyping platforms and freeware resources make it possible to widely expand phenotypic analysis tools for Arabidopsis. However, objective descriptors of shape parameters that could be used independently of the platform and segmentation software used are still lacking, and shape descriptions still rely on ad hoc or even contradictory descriptors, which could make comparisons difficult and perhaps inaccurate. Modern geometric morphometrics is a family of methods in quantitative biology proposed to be the main source of data and analytical tools in the emerging field of phenomics studies. Based on the location of landmarks (corresponding points) over imaged specimens and by combining geometry, multivariate analysis, and powerful statistical techniques, these tools offer the possibility to reproducibly and accurately account for shape variations among groups and measure them in shape distance units.

Results

Here, a particular scheme of landmark placement on Arabidopsis rosette images is proposed to study shape variation in viral infection processes. Shape differences between controls and infected plants are quantified throughout the infectious process and visualized. Quantitative comparisons between two unrelated ssRNA+ viruses are shown, and reproducibility issues are assessed.

Conclusions

Combined with the newest automated platforms and plant segmentation procedures, geometric morphometric tools could boost phenotypic features extraction and processing in an objective, reproducible manner.

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

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.

A "Do-It-Yourself" phenotyping system: measuring growth and morphology throughout the diel cycle in rosette shaped plants

BACKGROUND

Improvements in high-throughput phenotyping technologies are rapidly expanding the scope and capacity of plant biology studies to measure growth traits. Nevertheless, the costs of commercial phenotyping equipment and infrastructure remain prohibitively expensive for wide-scale uptake, while academic solutions can require significant local expertise. Here we present a low-cost methodology for plant biologists to build their own phenotyping system for quantifying growth rates and phenotypic characteristics of Arabidopsis thaliana rosettes throughout the diel cycle.

RESULTS

We constructed an image capture system consisting of a near infra-red (NIR, 940 nm) LED panel with a mounted Raspberry Pi NoIR camera and developed a MatLab-based software module (iDIEL Plant) to characterise rosette expansion. Our software was able to accurately segment and characterise multiple rosettes within an image, regardless of plant arrangement or genotype, and batch process image sets. To further validate our system, wild-type Arabidopsis plants (Col-0) and two mutant lines with reduced Rubisco contents, pale leaves and slow growth phenotypes (1a3b and 1a2b) were grown on a single plant tray. Plants were imaged from 9 to 24 days after germination every 20 min throughout the 24 h light-dark growth cycle (i.e. the diel cycle). The resulting dataset provided a dynamic and uninterrupted characterisation of differences in rosette growth and expansion rates over time for the three lines tested.

CONCLUSION

Our methodology offers a straightforward solution for setting up automated, scalable and low-cost phenotyping facilities in a wide range of lab environments that could greatly increase the processing power and scalability of Arabidopsis soil growth experiments.

Image-based Analysis to Study Plant Infection with Human Pathogens

Our growing awareness that contaminated plants, fresh fruits and vegetables are responsible for a significant proportion of food poisoning with pathogenic microorganisms indorses the demand to understand the interactions between plants and human pathogens. Today we understand that those pathogens do not merely survive on or within plants, they actively infect plant organisms by suppressing their immune system. Studies on the infection process and disease development used mainly physiological, genetic, and molecular approaches, and image-based analysis provides yet another method for this toolbox. Employed as an observational tool, it bears the potential for objective and high throughput approaches, and together with other methods it will be very likely a part of data fusion approaches in the near future.