SeedGerm: a cost-effective phenotyping platform for automated seed imaging and machine-learning based phenotypic analysis of crop seed germination

Digital techniques and trends for seed phenotyping using optical sensors

BACKGROUND

The breeding of high-quality, high-yield, and disease-resistant varieties is closely related to food security. The investigation of breeding results relies on the evaluation of seed phenotype, which is a key step in the process of breeding. In the global digitalization trend, digital technology based on optical sensors can perform the digitization of seed phenotype in a non-contact, high throughput way, thus significantly improving breeding efficiency.

AIM OF REVIEW

This paper provides a comprehensive overview of the principles, characteristics, data processing methods, and bottlenecks associated with three digital technique types based on optical sensors: spectroscopy, digital imaging, and three-dimensional (3D) reconstruction techniques. In addition, the applicability and adaptability of digital techniques based on the optical sensors of maize seed phenotype traits, namely external visible phenotype (EVP) and internal invisible phenotype (IIP), are investigated. Furthermore, trends in future equipment, platform, phenotype data, and processing algorithms are discussed. This review offers conceptual and practical support for seed phenotype digitization based on optical sensors, which will provide reference and guidance for future research.

KEY SCIENTIFIC CONCEPTS OF REVIEW

The digital techniques based on optical sensors can perform non-contact and high-throughput seed phenotype evaluation. Due to the distinct characteristics of optical sensors, matching suitable digital techniques according to seed phenotype traits can greatly reduce resource loss, and promote the efficiency of seed evaluation as well as breeding decision-making. Future research in phenotype equipment and platform, phenotype data, and processing algorithms will make digital techniques better meet the demands of seed phenotype evaluation, and promote automatic, integrated, and intelligent evaluation of seed phenotype, further helping to lessen the gap between digital techniques and seed phenotyping.

POMONA: a multiplatform software for modeling seed physiology

Seed physiology is related to functional and metabolic traits of the seed-seedling transition. In this sense, modeling the kinetics, uniformity and capacity of a seed sample plays a central role in designing strategies for trade, food, and environmental security. Thus, POMONA is presented as an easy-to-use multiplatform software designed to bring several logistic and linearized models into a single package, allowing for convenient and fast assessment of seed germination and or longevity, even if the data has a non-Normal distribution. POMONA is implemented in JavaScript using the Quasar framework and can run in the Microsoft Windows operating system, GNU/Linux, and Android-powered mobile hardware or on a web server as a service. The capabilities of POMONA are showcased through a series of examples with diaspores of corn and soybean, evidencing its robustness, accuracy, and performance. POMONA can be the first step for the creation of an automatic multiplatform that will benefit laboratory users, including those focused on image analysis.

Molecular dynamics of seed priming at the crossroads between basic and applied research

The potential of seed priming is still not fully exploited. Our limited knowledge of the molecular dynamics of seed pre-germinative metabolism is the main hindrance to more effective new-generation techniques. Climate change and other recent global crises are disrupting food security. To cope with the current demand for increased food, feed, and biofuel production, while preserving sustainability, continuous technological innovation should be provided to the agri-food sector. Seed priming, a pre-sowing technique used to increase seed vigor, has become a valuable tool due to its potential to enhance germination and stress resilience under changing environments. Successful priming protocols result from the ability to properly act on the seed pre-germinative metabolism and stimulate events that are crucial for seed quality. However, the technique still requires constant optimization, and researchers are committed to addressing some key open questions to overcome such drawbacks. In this review, an update of the current scientific and technical knowledge related to seed priming is provided. The rehydration-dehydration cycle associated with priming treatments can be described in terms of metabolic pathways that are triggered, modulated, or turned off, depending on the seed physiological stage. Understanding the ways seed priming affects, either positively or negatively, such metabolic pathways and impacts gene expression and protein/metabolite accumulation/depletion represents an essential step toward the identification of novel seed quality hallmarks. The need to expand the basic knowledge on the molecular mechanisms ruling the seed response to priming is underlined along with the strong potential of applied research on primed seeds as a source of seed quality hallmarks. This route will hasten the implementation of seed priming techniques needed to support sustainable agriculture systems.

Integrating biopolymer design with physical unclonable functions for anticounterfeiting and product traceability in agriculture

Smallholder farmers and manufacturers in the Agri-Food sector face substantial challenges because of increasing circulation of counterfeit products (e.g., seeds), for which current countermeasures are implemented mainly at the secondary packaging level, and are generally vulnerable because of limited security guarantees. Here, by integrating biopolymer design with physical unclonable functions (PUFs), we propose a cryptographic protocol for seed authentication using biodegradable and miniaturized PUF tags made of silk microparticles. By simply drop casting a mixture of variant silk microparticles on a seed surface, tamper-evident PUF tags can be seamlessly fabricated on a variety of seeds, where the unclonability comes from the stochastic assembly of spectrally and visually distinct silk microparticles in the tag. Unique, reproducible, and unpredictable PUF codes are generated from both Raman mapping and microscopy imaging of the silk tags. Together, the proposed technology offers a highly secure solution for anticounterfeiting and product traceability in agriculture.

A low-cost and open-source solution to automate imaging and analysis of cyst nematode infection assays for Arabidopsis thaliana

BACKGROUND

Cyst nematodes are one of the major groups of plant-parasitic nematode, responsible for considerable crop losses worldwide. Improving genetic resources, and therefore resistant cultivars, is an ongoing focus of many pest management strategies. One of the major bottlenecks in identifying the plant genes that impact the infection, and thus the yield, is phenotyping. The current available screening method is slow, has unidimensional quantification of infection limiting the range of scorable parameters, and does not account for phenotypic variation of the host. The ever-evolving field of computer vision may be the solution for both the above-mentioned issues. To utilise these tools, a specialised imaging platform is required to take consistent images of nematode infection in quick succession.

RESULTS

Here, we describe an open-source, easy to adopt, imaging hardware and trait analysis software method based on a pre-existing nematode infection screening method in axenic culture. A cost-effective, easy-to-build and -use, 3D-printed imaging device was developed to acquire images of the root system of Arabidopsis thaliana infected with the cyst nematode Heterodera schachtii, replacing costly microscopy equipment. Coupling the output of this device to simple analysis scripts allowed the measurement of some key traits such as nematode number and size from collected images, in a semi-automated manner. Additionally, we used this combined solution to quantify an additional trait, root area before infection, and showed both the confounding relationship of this trait on nematode infection and a method to account for it.

CONCLUSION

Taken together, this manuscript provides a low-cost and open-source method for nematode phenotyping that includes the biologically relevant nematode size as a scorable parameter, and a method to account for phenotypic variation of the host. Together these tools highlight great potential in aiding our understanding of nematode parasitism.

High-throughput screening paradigms in ecotoxicity testing: Emerging prospects and ongoing challenges

The rapidly increasing number of new production chemicals coupled with stringent implementation of global chemical management programs necessities a paradigm shift towards boarder uses of low-cost and high-throughput ecotoxicity testing strategies as well as deeper understanding of cellular and sub-cellular mechanisms of ecotoxicity that can be used in effective risk assessment. The latter will require automated acquisition of biological data, new capabilities for big data analysis as well as computational simulations capable of translating new data into in vivo relevance. However, very few efforts have been so far devoted into the development of automated bioanalytical systems in ecotoxicology. This is in stark contrast to standardized and high-throughput chemical screening and prioritization routines found in modern drug discovery pipelines. As a result, the high-throughput and high-content data acquisition in ecotoxicology is still in its infancy with limited examples focused on cell-free and cell-based assays. In this work we outline recent developments and emerging prospects of high-throughput bioanalytical approaches in ecotoxicology that reach beyond in vitro biotests. We discuss future importance of automated quantitative data acquisition for cell-free, cell-based as well as developments in phytotoxicity and in vivo biotests utilizing small aquatic model organisms. We also discuss recent innovations such as organs-on-a-chip technologies and existing challenges for emerging high-throughput ecotoxicity testing strategies. Lastly, we provide seminal examples of the small number of successful high-throughput implementations that have been employed in prioritization of chemicals and accelerated environmental risk assessment.

Phenotyping Fusarium head blight through seed morphology characteristics using RGB imaging

Fusarium head blight (FHB) is an economically important disease affecting wheat and thus poses a major threat to wheat production. Several studies have evaluated the effectiveness of image analysis methods to predict FHB using disease-infected grains; however, few have looked at the final application, considering the relationship between cost and benefit, resolution, and accuracy. The conventional screening of FHB resistance of large-scale samples is still dependent on low-throughput visual inspections. This study aims to compare the performance of two cost-benefit seed image analysis methods, the free software "SmartGrain" and the fully automated commercially available instrument "Cgrain Value™" by assessing 16 seed morphological traits of winter wheat to predict FHB. The analysis was carried out on a seed set of FHB which was visually assessed as to the severity. The dataset is composed of 432 winter wheat genotypes that were greenhouse-inoculated. The predictions from each method, in addition to the predictions combined from the results of both methods, were compared with the disease visual scores. The results showed that Cgrain Value™ had a higher prediction accuracy of R ² = 0.52 compared with SmartGrain for which R ² = 0.30 for all morphological traits. However, the results combined from both methods showed the greatest prediction performance of R ² = 0.58. Additionally, a subpart of the morphological traits, namely, width, length, thickness, and color features, showed a higher correlation with the visual scores compared with the other traits. Overall, both methods were related to the visual scores. This study shows that these affordable imaging methods could be effective to predict FHB in seeds and enable us to distinguish minor differences in seed morphology, which could lead to a precise performance selection of disease-free seeds/grains.

Automatic Monitoring System for Seed Germination Test Based on Deep Learning

Germination test is an irreplaceable step in seed selection and breeding. The current traditional germination test method must rely on experienced professional technicians to repeatedly classify and count the germination status of seeds and count the germination rate at different moments during the whole test process (usually takes 2 to 10 days). Currently, only the German seed germination detection system (Germination Scanalyzer) can solve this problem, but it is so expensive that it has not been practically promoted. In order to improve breeding efficiency, an automatic monitoring system for seed germination tests based on deep learning was designed. It includes a modified germination thermostat, connected with a three-dimensional movable camera bin with built-in camera; a multifunctional software system capable of online, offline, and sentinel mode monitoring; a dense distributed small target detection algorithm (DDST-CenterNet) for seed germination monitoring systems. The system test results show that the seed germination test automatic monitoring system is low cost, does not depend on the seed background, light, camera model, and other usage environments, and has high scalability. The DDST-CenterNet algorithm proposed in this paper can still maintain high accuracy and good stability in the process of seed target detection and classification as the number and density of seeds increase, which is suitable for a special application scenario of seed germination test. In addition, the algorithm has high computational efficiency and can give detection results at a frame rate of not less than 10fps, which can be used in practical applications.

Capturing crop adaptation to abiotic stress using image-based technologies

Farmers and breeders aim to improve crop responses to abiotic stresses and secure yield under adverse environmental conditions. To achieve this goal and select the most resilient genotypes, plant breeders and researchers rely on phenotyping to quantify crop responses to abiotic stress. Recent advances in imaging technologies allow researchers to collect physiological data non-destructively and throughout time, making it possible to dissect complex plant responses into quantifiable traits. The use of image-based technologies enables the quantification of crop responses to stress in both controlled environmental conditions and field trials. This paper summarizes phenotyping imaging technologies (RGB, multispectral and hyperspectral sensors, among others) that have been used to assess different abiotic stresses including salinity, drought and nitrogen deficiency, while discussing their advantages and drawbacks. We present a detailed review of traits involved in abiotic tolerance, which have been quantified by a range of imaging sensors under high-throughput phenotyping facilities or using unmanned aerial vehicles in the field. We also provide an up-to-date compilation of spectral tolerance indices and discuss the progress and challenges in machine learning, including supervised and unsupervised models as well as deep learning.

Objective Phenotyping of Root System Architecture Using Image Augmentation and Machine Learning in Alfalfa (Medicago sativa L.)

Active breeding programs specifically for root system architecture (RSA) phenotypes remain rare; however, breeding for branch and taproot types in the perennial crop alfalfa is ongoing. Phenotyping in this and other crops for active RSA breeding has mostly used visual scoring of specific traits or subjective classification into different root types. While image-based methods have been developed, translation to applied breeding is limited. This research is aimed at developing and comparing image-based RSA phenotyping methods using machine and deep learning algorithms for objective classification of 617 root images from mature alfalfa plants collected from the field to support the ongoing breeding efforts. Our results show that unsupervised machine learning tends to incorrectly classify roots into a normal distribution with most lines predicted as the intermediate root type. Encouragingly, random forest and TensorFlow-based neural networks can classify the root types into branch-type, taproot-type, and an intermediate taproot-branch type with 86% accuracy. With image augmentation, the prediction accuracy was improved to 97%. Coupling the predicted root type with its prediction probability will give breeders a confidence level for better decisions to advance the best and exclude the worst lines from their breeding program. This machine and deep learning approach enables accurate classification of the RSA phenotypes for genomic breeding of climate-resilient alfalfa.

Seed germination and vigor: ensuring crop sustainability in a changing climate

In the coming decades, maintaining a steady food supply for the increasing world population will require high-yielding crop plants which can be productive under increasingly variable conditions. Maintaining high yields will require the successful and uniform establishment of plants in the field under altered environmental conditions. Seed vigor, a complex agronomic trait that includes seed longevity, germination speed, seedling growth, and early stress tolerance, determines the duration and success of this establishment period. Elevated temperature during early seed development can decrease seed size, number, and fertility, delay germination and reduce seed vigor in crops such as cereals, legumes, and vegetable crops. Heat stress in mature seeds can reduce seed vigor in crops such as lettuce, oat, and chickpea. Warming trends and increasing temperature variability can increase seed dormancy and reduce germination rates, especially in crops that require lower temperatures for germination and seedling establishment. To improve seed germination speed and success, much research has focused on selecting quality seeds for replanting, priming seeds before sowing, and breeding varieties with improved seed performance. Recent strides in understanding the genetic basis of variation in seed vigor have used genomics and transcriptomics to identify candidate genes for improving germination, and several studies have explored the potential impact of climate change on the percentage and timing of germination. In this review, we discuss these recent advances in the genetic underpinnings of seed performance as well as how climate change is expected to affect vigor in current varieties of staple, vegetable, and other crops.

Advances in "Omics" Approaches for Improving Toxic Metals/Metalloids Tolerance in Plants

Food safety has emerged as a high-urgency matter for sustainable agricultural production. Toxic metal contamination of soil and water significantly affects agricultural productivity, which is further aggravated by extreme anthropogenic activities and modern agricultural practices, leaving food safety and human health at risk. In addition to reducing crop production, increased metals/metalloids toxicity also disturbs plants' demand and supply equilibrium. Counterbalancing toxic metals/metalloids toxicity demands a better understanding of the complex mechanisms at physiological, biochemical, molecular, cellular, and plant level that may result in increased crop productivity. Consequently, plants have established different internal defense mechanisms to cope with the adverse effects of toxic metals/metalloids. Nevertheless, these internal defense mechanisms are not adequate to overwhelm the metals/metalloids toxicity. Plants produce several secondary messengers to trigger cell signaling, activating the numerous transcriptional responses correlated with plant defense. Therefore, the recent advances in omics approaches such as genomics, transcriptomics, proteomics, metabolomics, ionomics, miRNAomics, and phenomics have enabled the characterization of molecular regulators associated with toxic metal tolerance, which can be deployed for developing toxic metal tolerant plants. This review highlights various response strategies adopted by plants to tolerate toxic metals/metalloids toxicity, including physiological, biochemical, and molecular responses. A seven-(omics)-based design is summarized with scientific clues to reveal the stress-responsive genes, proteins, metabolites, miRNAs, trace elements, stress-inducible phenotypes, and metabolic pathways that could potentially help plants to cope up with metals/metalloids toxicity in the face of fluctuating environmental conditions. Finally, some bottlenecks and future directions have also been highlighted, which could enable sustainable agricultural production.

CBM: An IoT Enabled LiDAR Sensor for In-Field Crop Height and Biomass Measurements

The phenotypic characterization of crop genotypes is an essential, yet challenging, aspect of crop management and agriculture research. Digital sensing technologies are rapidly advancing plant phenotyping and speeding-up crop breeding outcomes. However, off-the-shelf sensors might not be fully applicable and suitable for agricultural research due to the diversity in crop species and specific needs during plant breeding selections. Customized sensing systems with specialized sensor hardware and software architecture provide a powerful and low-cost solution. This study designed and developed a fully integrated Raspberry Pi-based LiDAR sensor named CropBioMass (CBM), enabled by internet of things to provide a complete end-to-end pipeline. The CBM is a low-cost sensor, provides high-throughput seamless data collection in field, small data footprint, injection of data onto the remote server, and automated data processing. The phenotypic traits of crop fresh biomass, dry biomass, and plant height that were estimated by CBM data had high correlation with ground truth manual measurements in a wheat field trial. The CBM is readily applicable for high-throughput plant phenotyping, crop monitoring, and management for precision agricultural applications.

Temperature during seed maturation controls seed vigour through ABA breakdown in the endosperm and causes a passive effect on DOG1 mRNA levels during entry into quiescence

Temperature variation during seed set is an important modulator of seed dormancy and impacts the performance of crop seeds through effects on establishment rate. It remains unclear how changing temperature during maturation leads to dormancy and growth vigour differences in nondormant seedlings. Here we take advantage of the large seed size in Brassica oleracea to analyse effects of temperature on individual seed tissues. We show that warm temperature during seed maturation promotes seed germination, while removal of the endosperm from imbibed seeds abolishes temperature-driven effects on germination. We demonstrate that cool temperatures during early seed maturation lead to abscisic acid (ABA) retention specifically in the endosperm at desiccation. During this time temperature affects ABA dynamics in individual seed tissues and regulates ABA catabolism. We also show that warm-matured seeds preinduce a subset of germination-related programmes in the endosperm, whereas cold-matured seeds continue to store maturation-associated transcripts including DOG1 because of effects on mRNA degradation before quiescence, rather than because of the effect of temperature on transcription. We propose that effects of temperature on seed vigour are explained by endospermic ABA breakdown and the divergent relationships between temperature and mRNA breakdown and between temperature, seed moisture and the glass transition.

Large-scale field phenotyping using backpack LiDAR and CropQuant-3D to measure structural variation in wheat

Plant phenomics bridges the gap between traits of agricultural importance and genomic information. Limitations of current field-based phenotyping solutions include mobility, affordability, throughput, accuracy, scalability, and the ability to analyze big data collected. Here, we present a large-scale phenotyping solution that combines a commercial backpack Light Detection and Ranging (LiDAR) device and our analytic software, CropQuant-3D, which have been applied jointly to phenotype wheat (Triticum aestivum) and associated 3D trait analysis. The use of LiDAR can acquire millions of 3D points to represent spatial features of crops, and CropQuant-3D can extract meaningful traits from large, complex point clouds. In a case study examining the response of wheat varieties to three different levels of nitrogen fertilization in field experiments, the combined solution differentiated significant genotype and treatment effects on crop growth and structural variation in the canopy, with strong correlations with manual measurements. Hence, we demonstrate that this system could consistently perform 3D trait analysis at a larger scale and more quickly than heretofore possible and addresses challenges in mobility, throughput, and scalability. To ensure our work could reach non-expert users, we developed an open-source graphical user interface for CropQuant-3D. We, therefore, believe that the combined system is easy-to-use and could be used as a reliable research tool in multi-location phenotyping for both crop research and breeding. Furthermore, together with the fast maturity of LiDAR technologies, the system has the potential for further development in accuracy and affordability, contributing to the resolution of the phenotyping bottleneck and exploiting available genomic resources more effectively.

Sustainable Agriculture through Multidisciplinary Seed Nanopriming: Prospects of Opportunities and Challenges

The global community decided in 2015 to improve people's lives by 2030 by setting 17 global goals for sustainable development. The second goal of this community was to end hunger. Plant seeds are an essential input in agriculture; however, during their developmental stages, seeds can be negatively affected by environmental stresses, which can adversely affect seed vigor, seedling establishment, and crop production. Seeds resistant to high salinity, droughts and climate change can result in higher crop yield. The major findings suggested in this review refer nanopriming as an emerging seed technology towards sustainable food amid growing demand with the increasing world population. This novel growing technology could influence the crop yield and ensure the quality and safety of seeds, in a sustainable way. When nanoprimed seeds are germinated, they undergo a series of synergistic events as a result of enhanced metabolism: modulating biochemical signaling pathways, trigger hormone secretion, reduce reactive oxygen species leading to improved disease resistance. In addition to providing an overview of the challenges and limitations of seed nanopriming technology, this review also describes some of the emerging nano-seed priming methods for sustainable agriculture, and other technological developments using cold plasma technology and machine learning.

MFCIS: an automatic leaf-based identification pipeline for plant cultivars using deep learning and persistent homology

Recognizing plant cultivars reliably and efficiently can benefit plant breeders in terms of property rights protection and innovation of germplasm resources. Although leaf image-based methods have been widely adopted in plant species identification, they seldom have been applied in cultivar identification due to the high similarity of leaves among cultivars. Here, we propose an automatic leaf image-based cultivar identification pipeline called MFCIS (Multi-feature Combined Cultivar Identification System), which combines multiple leaf morphological features collected by persistent homology and a convolutional neural network (CNN). Persistent homology, a multiscale and robust method, was employed to extract the topological signatures of leaf shape, texture, and venation details. A CNN-based algorithm, the Xception network, was fine-tuned for extracting high-level leaf image features. For fruit species, we benchmarked the MFCIS pipeline on a sweet cherry (Prunus avium L.) leaf dataset with >5000 leaf images from 88 varieties or unreleased selections and achieved a mean accuracy of 83.52%. For annual crop species, we applied the MFCIS pipeline to a soybean (Glycine max L. Merr.) leaf dataset with 5000 leaf images of 100 cultivars or elite breeding lines collected at five growth periods. The identification models for each growth period were trained independently, and their results were combined using a score-level fusion strategy. The classification accuracy after score-level fusion was 91.4%, which is much higher than the accuracy when utilizing each growth period independently or mixing all growth periods. To facilitate the adoption of the proposed pipelines, we constructed a user-friendly web service, which is freely available at http://www.mfcis.online .

SeedQuant: a deep learning-based tool for assessing stimulant and inhibitor activity on root parasitic seeds

Witchweeds (Striga spp.) and broomrapes (Orobanchaceae and Phelipanche spp.) are root parasitic plants that infest many crops in warm and temperate zones, causing enormous yield losses and endangering global food security. Seeds of these obligate parasites require rhizospheric, host-released stimulants to germinate, which opens up possibilities for controlling them by applying specific germination inhibitors or synthetic stimulants that induce lethal germination in the host's absence. To determine their effect on germination, root exudates or synthetic stimulants/inhibitors are usually applied to parasitic seeds in in vitro bioassays, followed by assessment of germination ratios. Although these protocols are very sensitive, the germination recording process is laborious, representing a challenge for researchers and impeding high-throughput screens. Here, we developed an automatic seed census tool to count and discriminate germinated seeds (GS) from non-GS. We combined deep learning, a powerful data-driven framework that can accelerate the procedure and increase its accuracy, for object detection with computer vision latest development based on the Faster Region-based Convolutional Neural Network algorithm. Our method showed an accuracy of 94% in counting seeds of Striga hermonthica and reduced the required time from approximately 5 min to 5 s per image. Our proposed software, SeedQuant, will be of great help for seed germination bioassays and enable high-throughput screening for germination stimulants/inhibitors. SeedQuant is an open-source software that can be further trained to count different types of seeds for research purposes.

Applications of deep-learning approaches in horticultural research: a review

Deep learning is known as a promising multifunctional tool for processing images and other big data. By assimilating large amounts of heterogeneous data, deep-learning technology provides reliable prediction results for complex and uncertain phenomena. Recently, it has been increasingly used by horticultural researchers to make sense of the large datasets produced during planting and postharvest processes. In this paper, we provided a brief introduction to deep-learning approaches and reviewed 71 recent research works in which deep-learning technologies were applied in the horticultural domain for variety recognition, yield estimation, quality detection, stress phenotyping detection, growth monitoring, and other tasks. We described in detail the application scenarios reported in the relevant literature, along with the applied models and frameworks, the used data, and the overall performance results. Finally, we discussed the current challenges and future trends of deep learning in horticultural research. The aim of this review is to assist researchers and provide guidance for them to fully understand the strengths and possible weaknesses when applying deep learning in horticultural sectors. We also hope that this review will encourage researchers to explore some significant examples of deep learning in horticultural science and will promote the advancement of intelligent horticulture.

ScreenSeed as a novel high throughput seed germination phenotyping method

A high throughput phenotyping tool for seed germination, the ScreenSeed technology, was developed with the aim of screening genotype responsiveness and chemical drugs. This technology was presently used with Arabidopsis thaliana seeds to allow characterizing seed samples germination behavior by incubating seeds in 96-well microplates under defined conditions and detecting radicle protrusion through the seed coat by automated image analysis. This study shows that this technology provides a fast procedure allowing to handle thousands of seeds without compromising repeatability or accuracy of the germination measurements. Potential biases of the experimental protocol were assessed through statistical analyses of germination kinetics. Comparison of the ScreenSeed procedure with commonly used germination tests based upon visual scoring displayed very similar germination kinetics.

"Macrobot": An Automated Segmentation-Based System for Powdery Mildew Disease Quantification

Managing plant diseases is increasingly difficult due to reasons such as intensifying the field production, climatic change-driven expansion of pests, redraw and loss of effectiveness of pesticides, rapid breakdown of the disease resistance in the field, and other factors. The substantial progress in genomics of both plants and pathogens, achieved in the last decades, has the potential to counteract this negative trend, however, only when the genomic data is supported by relevant phenotypic data that allows linking the genomic information to specific traits. We have developed a set of methods and equipment and combined them into a "Macrophenomics facility." The pipeline has been optimized for the quantification of powdery mildew infection symptoms on wheat and barley, but it can be adapted to other diseases and host plants. The Macrophenomics pipeline scores the visible powdery mildew disease symptoms, typically 5-7 days after inoculation (dai), in a highly automated manner. The system can precisely and reproducibly quantify the percentage of the infected leaf area with a theoretical throughput of up to 10000 individual samples per day, making it appropriate for phenotyping of large germplasm collections and crossing populations.

Coffee Flower Identification Using Binarization Algorithm Based on Convolutional Neural Network for Digital Images

Crop-type identification is one of the most significant applications of agricultural remote sensing, and it is important for yield estimation prediction and field management. At present, crop identification using datasets from unmanned aerial vehicle (UAV) and satellite platforms have achieved state-of-the-art performances. However, accurate monitoring of small plants, such as the coffee flower, cannot be achieved using datasets from these platforms. With the development of time-lapse image acquisition technology based on ground-based remote sensing, a large number of small-scale plantation datasets with high spatial-temporal resolution are being generated, which can provide great opportunities for small target monitoring of a specific region. The main contribution of this paper is to combine the binarization algorithm based on OTSU and the convolutional neural network (CNN) model to improve coffee flower identification accuracy using the time-lapse images (i.e., digital images). A certain number of positive and negative samples are selected from the original digital images for the network model training. Then, the pretrained network model is initialized using the VGGNet and trained using the constructed training datasets. Based on the well-trained CNN model, the coffee flower is initially extracted, and its boundary information can be further optimized by using the extracted coffee flower result of the binarization algorithm. Based on the digital images with different depression angles and illumination conditions, the performance of the proposed method is investigated by comparison of the performances of support vector machine (SVM) and CNN model. Hence, the experimental results show that the proposed method has the ability to improve coffee flower classification accuracy. The results of the image with a 52.5° angle of depression under soft lighting conditions are the highest, and the corresponding Dice (F1) and intersection over union (IoU) have reached 0.80 and 0.67, respectively.

High-Throughput in situ Root Image Segmentation Based on the Improved DeepLabv3+ Method

The Rhizotrons method is an important means of detecting dynamic growth and development phenotypes of plant roots. However, the segmentation of root images is a critical obstacle restricting further development of this method. At present, researchers mostly use direct manual drawings or software-assisted manual drawings to segment root systems for analysis. Root systems can be segmented from root images obtained by the Rhizotrons method, and then, root system lengths and diameters can be obtained with software. This type of image segmentation method is extremely inefficient and very prone to human error. Here, we investigate the effectiveness of an automated image segmentation method based on the DeepLabv3+ convolutional neural network (CNN) architecture to streamline such measurements. We have improved the upsampling portion of the DeepLabv3+ network and validated it using in situ images of cotton roots obtained with a micro root window root system monitoring system. Segmentation performance of the proposed method utilizing WinRHIZO Tron MF analysis was assessed using these images. After 80 epochs of training, the final verification set F1-score, recall, and precision were 0.9773, 0.9847, and 0.9702, respectively. The Spearman rank correlation between the manually obtained Rhizotrons manual segmentation root length and automated root length was 0.9667 (p < 10^-8), with r ² = 0.9449. Based on the comparison of our segmentation results with those of traditional manual and U-net segmentation methods, this novel method can more accurately segment root systems in complex soil environments. Thus, using the improved DeepLabv3+ to segment root systems based on micro-root images is an effective method for accurately and quickly segmenting root systems in a homogeneous soil environment and has clear advantages over traditional manual segmentation.

"Macrobot": An Automated Segmentation-Based System for Powdery Mildew Disease Quantification

Managing plant diseases is increasingly difficult due to reasons such as intensifying the field production, climatic change-driven expansion of pests, redraw and loss of effectiveness of pesticides, rapid breakdown of the disease resistance in the field, and other factors. The substantial progress in genomics of both plants and pathogens, achieved in the last decades, has the potential to counteract this negative trend, however, only when the genomic data is supported by relevant phenotypic data that allows linking the genomic information to specific traits. We have developed a set of methods and equipment and combined them into a "Macrophenomics facility." The pipeline has been optimized for the quantification of powdery mildew infection symptoms on wheat and barley, but it can be adapted to other diseases and host plants. The Macrophenomics pipeline scores the visible powdery mildew disease symptoms, typically 5-7 days after inoculation (dai), in a highly automated manner. The system can precisely and reproducibly quantify the percentage of the infected leaf area with a theoretical throughput of up to 10000 individual samples per day, making it appropriate for phenotyping of large germplasm collections and crossing populations.