Evaluation of the SeedCounter, A Mobile Application for Grain Phenotyping

An android-smartphone application for rice panicle detection and rice growth stage recognition using a lightweight YOLO network

Introduction

Detection of rice panicles and recognition of rice growth stages can significantly improve precision field management, which is crucial for maximizing grain yield. This study explores the use of deep learning on mobile phones as a platform for rice phenotype applications.

Methods

An improved YOLOv8 model, named YOLO_Efficient Computation Optimization (YOLO_ECO), was proposed to detect rice panicles at the booting, heading, and filling stages, and to recognize growth stages. YOLO_ECO introduced key improvements, including the C2f-FasterBlock-Effective Multi-scale Attention (C2f-Faster-EMA) replacing the original C2f module in the backbone, adoption of Slim Neck to reduce neck complexity, and the use of a Lightweight Shared Convolutional Detection (LSCD) head to enhance efficiency. An Android application, YOLO-RPD, was developed to facilitate rice phenotype detection in complex field environments.

Results and discussion

The performance impact of YOLO-RPD using models with different backbone networks, quantitative models, and input image sizes was analyzed. Experimental results demonstrated that YOLO_ECO outperformed traditional deep learning models, achieving average precision values of 96.4%, 93.2%, and 81.5% at the booting, heading, and filling stages, respectively. Furthermore, YOLO_ECO exhibited advantages in detecting occlusion and small panicles, while significantly optimizing parameter count, computational demand, and model size. The YOLO_ECO FP32-1280 achieved a mean average precision (mAP) of 90.4%, with 1.8 million parameters and 4.1 billion floating-point operations (FLOPs). The YOLO-RPD application demonstrates the feasibility of deploying deep learning models on mobile devices for precision agriculture, providing rice growers with a practical, lightweight tool for real-time monitoring.

Identification of Novel Loci Precisely Modulating Pre-Harvest Sprouting Resistance and Red Color Components of the Seed Coat in T. aestivum L

The association between pre-harvest sprouting (PHS) and seed coat color has long been recognized. Red-grained wheats generally exhibit greater PHS resistance compared to white-grained wheat, although variability in PHS resistance exists within red-grained varieties. Here, we conducted a genome-wide association study on a panel consisting of red-grained wheat varieties, aimed at uncovering genes that modulate PHS resistance and red color components of seed coat using digital image processing. Twelve loci associated with PHS traits were identified, nine of which were described for the first time. Genetic loci marked by SNPs AX-95172164 (chromosome 1B) and AX-158544327 (chromosome 7D) explained approximately 25% of germination index variance, highlighting their value for breeding PHS-resistant varieties. The most promising candidate gene for PHS resistance was TraesCS6B02G147900, encoding a protein involved in aleurone layer morphogenesis. Twenty-six SNPs were significantly associated with grain color, independently of the known Tamyb10 gene. Most of them were related to multiple color characteristics. Prioritization of genes within the revealed loci identified TraesCS1D03G0758600 and TraesCS7B03G1296800, involved in the regulation of pigment biosynthesis and in controlling pigment accumulation. In conclusion, our study identifies new loci associated with grain color and germination index, providing insights into the genetic mechanisms underlying these traits.

PhenoApp: A mobile tool for plant phenotyping to record field and greenhouse observations

With the ongoing cost decrease of genotyping and sequencing technologies, accurate and fast phenotyping remains the bottleneck in the utilizing of plant genetic resources for breeding and breeding research. Although cost-efficient high-throughput phenotyping platforms are emerging for specific traits and/or species, manual phenotyping is still widely used and is a time- and money-consuming step. Approaches that improve data recording, processing or handling are pivotal steps towards the efficient use of genetic resources and are demanded by the research community. Therefore, we developed PhenoApp, an open-source Android app for tablets and smartphones to facilitate the digital recording of phenotypical data in the field and in greenhouses. It is a versatile tool that offers the possibility to fully customize the descriptors/scales for any possible scenario, also in accordance with international information standards such as MIAPPE (Minimum Information About a Plant Phenotyping Experiment) and FAIR (Findable, Accessible, Interoperable, and Reusable) data principles. Furthermore, PhenoApp enables the use of pre-integrated ready-to-use BBCH (Biologische Bundesanstalt für Land- und Forstwirtschaft, Bundessortenamt und CHemische Industrie) scales for apple, cereals, grapevine, maize, potato, rapeseed and rice. Additional BBCH scales can easily be added. The simple and adaptable structure of input and output files enables an easy data handling by either spreadsheet software or even the integration in the workflow of laboratory information management systems (LIMS). PhenoApp is therefore a decisive contribution to increase efficiency of digital data acquisition in genebank management but also contributes to breeding and breeding research by accelerating the labour intensive and time-consuming acquisition of phenotyping data.

PhenoApp: A mobile tool for plant phenotyping to record field and greenhouse observations

With the ongoing cost decrease of genotyping and sequencing technologies, accurate and fast phenotyping remains the bottleneck in the utilizing of plant genetic resources for breeding and breeding research. Although cost-efficient high-throughput phenotyping platforms are emerging for specific traits and/or species, manual phenotyping is still widely used and is a time- and money-consuming step. Approaches that improve data recording, processing or handling are pivotal steps towards the efficient use of genetic resources and are demanded by the research community. Therefore, we developed PhenoApp, an open-source Android app for tablets and smartphones to facilitate the digital recording of phenotypical data in the field and in greenhouses. It is a versatile tool that offers the possibility to fully customize the descriptors/scales for any possible scenario, also in accordance with international information standards such as MIAPPE (Minimum Information About a Plant Phenotyping Experiment) and FAIR (Findable, Accessible, Interoperable, and Reusable) data principles. Furthermore, PhenoApp enables the use of pre-integrated ready-to-use BBCH (Biologische Bundesanstalt für Land- und Forstwirtschaft, Bundessortenamt und CHemische Industrie) scales for apple, cereals, grapevine, maize, potato, rapeseed and rice. Additional BBCH scales can easily be added. The simple and adaptable structure of input and output files enables an easy data handling by either spreadsheet software or even the integration in the workflow of laboratory information management systems (LIMS). PhenoApp is therefore a decisive contribution to increase efficiency of digital data acquisition in genebank management but also contributes to breeding and breeding research by accelerating the labour intensive and time-consuming acquisition of phenotyping data.

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.

QTL Analysis for Bread Wheat Seed Size, Shape and Color Characteristics Estimated by Digital Image Processing

The size, shape, and color of wheat seeds are important traits that are associated with yield and flour quality (size, shape), nutritional value, and pre-harvest sprouting (coat color). These traits are under multigenic control, and to dissect their molecular and genetic basis, quantitative trait loci (QTL) analysis is used. We evaluated 114 recombinant inbred lines (RILs) in a bi-parental RIL mapping population (the International Triticeae Mapping Initiative, ITMI/MP) grown in 2014 season. We used digital image analysis for seed phenotyping and obtained data for seven traits describing seed size and shape and 48 traits of seed coat color. We identified 212 additive and 34 pairs of epistatic QTLs on all the chromosomes of wheat genome except chromosomes 1A and 5D. Many QTLs were overlapping. We demonstrated that the overlap between QTL regions was low for seed size/shape traits and high for coat color traits. Using the literature and KEGG data, we identified sets of genes in Arabidopsis and rice from the networks controlling seed size and color. Further, we identified 29 and 14 candidate genes for seed size-related loci and for loci associated with seed coat color, respectively.

Stimulation of antioxidant activity and γ-aminobutyric acid synthesis in germinated wheat grain Triticum aestivum L. by ultrasound: Increasing the nutritional value of the product

The use of ultrasound to intensify the germination process of Triticum aestivum L. wheat was studied. This method of controlled germination can be used in several sectors of food industry, in particular in bakery. The effect of low-frequency ultrasound (20 kHz) at different intensities and duration on the germination process of Triticum aestivum L. wheat was systematically studied. We have found that 3-minute processing at 227 W/l output reduces the duration of wheat grain germination by 25% (12 ± 2 h) compared to the control samples. The use of ultrasound stimulated γ-aminobutyric acid (GABA) synthesis (18.9 ± 0.5 mg/100 g), increased the antioxidant activity (AOA) (2.86 ± 0.2 mg/g Trolox equivalents) and the amount of flavonoids (0.19 ± 0.03 mg QE/g). The SEM analysis of powder particles of whole-wheat flour made from wheat germinated with ultrasound exposure showed densely packed aggregates of protein matrix. To sum up, controlled ultrasound during wheat grain germination increases the amount of GABA and AOA. The whole-wheat flour is useful for food enrichment.

An Intelligent Analysis Method for 3D Wheat Grain and Ventral Sulcus Traits Based on Structured Light Imaging

The wheat grain three-dimensional (3D) phenotypic characters are of great significance for final yield and variety breeding, and the ventral sulcus traits are the important factors to the wheat flour yield. The wheat grain trait measurements are necessary; however, the traditional measurement method is still manual, which is inefficient, subjective, and labor intensive; moreover, the ventral sulcus traits can only be obtained by destructive measurement. In this paper, an intelligent analysis method based on the structured light imaging has been proposed to extract the 3D wheat grain phenotypes and ventral sulcus traits. First, the 3D point cloud data of wheat grain were obtained by the structured light scanner, and then, the specified point cloud processing algorithms including single grain segmentation and ventral sulcus location have been designed; finally, 28 wheat grain 3D phenotypic characters and 4 ventral sulcus traits have been extracted. To evaluate the best experimental conditions, three-level orthogonal experiments, which include rotation angle, scanning angle, and stage color factors, were carried out on 125 grains of 5 wheat varieties, and the results demonstrated that optimum conditions of rotation angle, scanning angle, and stage color were 30°, 37°, black color individually. Additionally, the results also proved that the mean absolute percentage errors (MAPEs) of wheat grain length, width, thickness, and ventral sulcus depth were 1.83, 1.86, 2.19, and 4.81%. Moreover, the 500 wheat grains of five varieties were used to construct and validate the wheat grain weight model by 32 phenotypic traits, and the cross-validation results showed that the R 2 of the models ranged from 0.77 to 0.83. Finally, the wheat grain phenotype extraction and grain weight prediction were integrated into the specialized software. Therefore, this method was demonstrated to be an efficient and effective way for wheat breeding research.

Wheat Seed Classification: Utilizing Ensemble Machine Learning Approach

Recognizing and authenticating wheat varieties is critical for quality evaluation in the grain supply chain, particularly for methods for seed inspection. Recognition and verification of grains are carried out manually through direct visual examination. Automatic categorization techniques based on machine learning and computer vision offered fast and high-throughput solutions. Even yet, categorization remains a complicated process at the varietal level. The paper utilized machine learning approaches for classifying wheat seeds. The seed classification is performed based on 7 physical features: area of wheat, perimeter of wheat, compactness, length of the kernel, width of the kernel, asymmetry coefficient, and kernel groove length. The dataset is collected from the UCI library and has 210 occurrences of wheat kernels. The dataset contains kernels from three wheat varieties Kama, Rosa, and Canadian, with 70 components chosen at random for the experiment. In the first phase, K-nearest neighbor, classification and regression tree, and Gaussian Naïve Bayes algorithms are implemented for classification. The results of these algorithms are compared with the ensemble approach of machine learning. The results reveal that accuracies calculated for KNN, decision, and Naïve Bayes classifiers are 92%, 94%, and 92%, respectively. The highest accuracy of 95% is achieved through the ensemble classifier in which decision is made based on hard voting.

Deep learning based high-throughput phenotyping of chalkiness in rice exposed to high night temperature

BACKGROUND

Rice is a major staple food crop for more than half the world's population. As the global population is expected to reach 9.7 billion by 2050, increasing the production of high-quality rice is needed to meet the anticipated increased demand. However, global environmental changes, especially increasing temperatures, can affect grain yield and quality. Heat stress is one of the major causes of an increased proportion of chalkiness in rice, which compromises quality and reduces the market value. Researchers have identified 140 quantitative trait loci linked to chalkiness mapped across 12 chromosomes of the rice genome. However, the available genetic information acquired by employing advances in genetics has not been adequately exploited due to a lack of a reliable, rapid and high-throughput phenotyping tool to capture chalkiness. To derive extensive benefit from the genetic progress achieved, tools that facilitate high-throughput phenotyping of rice chalkiness are needed.

RESULTS

We use a fully automated approach based on convolutional neural networks (CNNs) and Gradient-weighted Class Activation Mapping (Grad-CAM) to detect chalkiness in rice grain images. Specifically, we train a CNN model to distinguish between chalky and non-chalky grains and subsequently use Grad-CAM to identify the area of a grain that is indicative of the chalky class. The area identified by the Grad-CAM approach takes the form of a smooth heatmap that can be used to quantify the degree of chalkiness. Experimental results on both polished and unpolished rice grains using standard instance classification and segmentation metrics have shown that Grad-CAM can accurately identify chalky grains and detect the chalkiness area.

CONCLUSIONS

We have successfully demonstrated the application of a Grad-CAM based tool to accurately capture high night temperature induced chalkiness in rice. The models trained will be made publicly available. They are easy-to-use, scalable and can be readily incorporated into ongoing rice breeding programs, without rice researchers requiring computer science or machine learning expertise.

Classification of Fruit Flies by Gender in Images Using Smartphones and the YOLOv4-Tiny Neural Network

The fruit fly Drosophila melanogaster is a classic research object in genetics and systems biology. In the genetic analysis of flies, a routine task is to determine the offspring size and gender ratio in their populations. Currently, these estimates are made manually, which is a very time-consuming process. The counting and gender determination of flies can be automated by using image analysis with deep learning neural networks on mobile devices. We proposed an algorithm based on the YOLOv4-tiny network to identify Drosophila flies and determine their gender based on the protocol of taking pictures of insects on a white sheet of paper with a cell phone camera. Three strategies with different types of augmentation were used to train the network. The best performance (F1 = 0.838) was achieved using synthetic images with mosaic generation. Females gender determination is worse than that one of males. Among the factors that most strongly influencing the accuracy of fly gender recognition, the fly’s position on the paper was the most important. Increased light intensity and higher quality of the device cameras have a positive effect on the recognition accuracy. We implement our method in the FlyCounter Android app for mobile devices, which performs all the image processing steps using the device processors only. The time that the YOLOv4-tiny algorithm takes to process one image is less than 4 s.

Fine Mapping of a Vigor QTL in Chickpea (Cicer arietinum L.) Reveals a Potential Role for Ca4_TIFY4B in Regulating Leaf and Seed Size

Plant vigor is a complex trait for which the underlying molecular control mechanisms remain unclear. Vigorous plants tend to derive from larger seeds and have greater early canopy cover, often with bigger leaves. In this study, we delimited the size of a major vigor quantitative trait locus (QTL) on chickpea chromosome 4-104.4 kb, using recombinant association analysis in 15 different heterogeneous inbred families, derived from a Rupali/Genesis836 recombinant inbred line population. The phenotypic and molecular genetic analysis provided evidence for a role of the gene Ca4_TIFY4B, in determining leaf and seed size in chickpea. A non-synonymous single-nucleotide polymorphism (SNP) in the high-vigor parent was located inside the core motif TIFYCG, resulting in a residue change T[I/S]FYCG. Complexes formed by orthologs of Ca4_TIFY4B (PEAPOD in Arabidopsis), Novel Interactor of JAZ (CaNINJA), and other protein partners are reported to act as repressors regulating the transcription of downstream genes that control plant organ size. When tested in a yeast 2-hybrid (Y2H) assay, this residue change suppressed the interaction between Ca4_TIFY4B and CaNINJA. This is the first report of a naturally occurring variant of the TIFY family in plants. A robust gene-derived molecular marker is available for selection in chickpea for seed and plant organ size, i.e., key component traits of vigor.

High-Throughput Extraction of Seed Traits Using Image Acquisition and Analysis

Seed traits can easily be assessed using image processing tools to evaluate differences in crop variety performances in response to environment and stress. In this chapter, we describe a protocol to measure seed traits that can be applied to crops with small grains, including legume grains with little modification. The imaging processing tool can be applied to process a batch of images without human intervention. The method allows evaluation of geometric and color features, and currently extracts 11 seed traits that include number of seeds, seed area, major axis, minor axis, eccentricity, and mean and standard deviation of reflectance in red, green, and blue channels from seed images. Protocols or methods, including the one described in this chapter, facilitate phenotyping seed traits in a high-throughput and automated manner, which can be applied in plant breeding programs and food processing industry to evaluate seed quality.

Relationship between the Characteristics of Bread Wheat Grains, Storage Time and Germination

Seed storage is important to farmers, breeders and for germplasm preservation. During storage, seeds accumulate damage at the structural and metabolic level, which disrupt their function and reduce resistance to adverse external conditions. In this regard, issues related to seed aging prove to be relevant for maintaining the viability of genetic collections. We analyzed morphological characteristics of grains and their coat color for 44 recombinant inbred lines (RILs) of bread wheat grown in four different seasons, 2003, 2004, 2009 and 2014. Our investigations were performed in 2020. For 19 RILs from the same seasons germination was evaluated. Our results demonstrate that genotype significantly affects the variability of all seed traits, and the year of harvesting affects about 80% of them (including all the traits of shape and size). To identify the trend between changes in grain characteristics and harvesting year, we estimated correlation coefficients between them. No significant trend was detected for the grain shape/size traits, while 90% of the color traits demonstrated such a trend. The most significant negative correlations were found between the harvesting year and the traits of grain redness: the greater the storage time, the more intensive is red color component for the grains. At the same time, it was shown that grains of longer storage time (earlier harvesting year) have lighter coat. Analysis of linear correlations between germination of wheat seeds of different genotypes and harvesting years and their seed traits revealed a negative linear relationship between the red component of coat color and germination: the redder the grains, the lower their germination rate. The results obtained demonstrate manifestations of metabolic changes in the coat of grains associated with storage time and their relationship with a decrease of seed viability.

Integrating Genomic and Phenomic Approaches to Support Plant Genetic Resources Conservation and Use

Plant genebanks provide genetic resources for breeding and research programs worldwide. These programs benefit from having access to high-quality, standardized phenotypic and genotypic data. Technological advances have made it possible to collect phenomic and genomic data for genebank collections, which, with the appropriate analytical tools, can directly inform breeding programs. We discuss the importance of considering genebank accession homogeneity and heterogeneity in data collection and documentation. Citing specific examples, we describe how well-documented genomic and phenomic data have met or could meet the needs of plant genetic resource managers and users. We explore future opportunities that may emerge from improved documentation and data integration among plant genetic resource information systems.

TaGRF3-2A Improves Some Agronomically Valuable Traits in Semi-Dwarf Spring Triticale

The breeding improvement of triticale is tightly associated with the introgression of dwarfing genes, in particular, gibberellin (GA)-insensitive Ddw1 from rye. Despite the increase in harvest index and resistance to lodging, this gene adversely affects grain weight and size. Growth regulation factor (GRF) genes are plant-specific transcription factors that play an important role in plant growth, including GA-induced stem elongation. This study presents the results of a two-year field experiment to assess the effect of alleles of the TaGRF3-2A gene in interaction with DDW1 on economically valuable traits of spring triticale plants grown in the Non-Chernozem zone. Our results show that, depending on the allelic state, the TaGRF3-2A gene in semi-dwarf spring triticale plants influences the thousand grain weight and the grain weight of the main spike in spring triticale, which makes it possible to use it to compensate for the negative effects of the dwarfing allele Ddw1. The identified allelic variants of the TaGRF3-2A gene can be included in marker-assisted breeding for triticale to improve traits.

Computer Vision and Machine Learning Analysis of Commercial Rice Grains: A Potential Digital Approach for Consumer Perception Studies

Rice quality assessment is essential for meeting high-quality standards and consumer demands. However, challenges remain in developing cost-effective and rapid techniques to assess commercial rice grain quality traits. This paper presents the application of computer vision (CV) and machine learning (ML) to classify commercial rice samples based on dimensionless morphometric parameters and color parameters extracted using CV algorithms from digital images obtained from a smartphone camera. The artificial neural network (ANN) model was developed using nine morpho-colorimetric parameters to classify rice samples into 15 commercial rice types. Furthermore, the ANN models were deployed and evaluated on a different imaging system to simulate their practical applications under different conditions. Results showed that the best classification accuracy was obtained using the Bayesian Regularization (BR) algorithm of the ANN with ten hidden neurons at 91.6% (MSE = <0.01) and 88.5% (MSE = 0.01) for the training and testing stages, respectively, with an overall accuracy of 90.7% (Model 2). Deployment also showed high accuracy (93.9%) in the classification of the rice samples. The adoption by the industry of rapid, reliable, and accurate methods, such as those presented here, may allow the incorporation of different morpho-colorimetric traits in rice with consumer perception studies.

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.

GridFree: a python package of imageanalysis for interactive grain counting and measuring

Grain characteristics, including kernel length, kernel width, and thousand kernel weight, are critical component traits for grain yield. Manual measurements and counting are expensive, forming the bottleneck for dissecting these traits' genetic architectures toward ultimate yield improvement. High-throughput phenotyping methods have been developed by analyzing images of kernels. However, segmenting kernels from the image background and noise artifacts or from other kernels positioned in close proximity remain as challenges. In this study, we developed a software package, named GridFree, to overcome these challenges. GridFree uses an unsupervised machine learning approach, K-Means, to segment kernels from the background by using principal component analysis on both raw image channels and their color indices. GridFree incorporates users' experiences as a dynamic criterion to set thresholds for a divide-and-combine strategy that effectively segments adjacent kernels. When adjacent multiple kernels are incorrectly segmented as a single object, they form an outlier on the distribution plot of kernel area, length, and width. GridFree uses the dynamic threshold settings for splitting and merging. In addition to counting, GridFree measures kernel length, width, and area with the option of scaling with a reference object. Evaluations against existing software programs demonstrated that GridFree had the smallest error on counting seeds for multiple crop species. GridFree was implemented in Python with a friendly graphical user interface to allow users to easily visualize the outcomes and make decisions, which ultimately eliminates time-consuming and repetitive manual labor. GridFree is freely available at the GridFree website (https://zzlab.net/GridFree).

High-Throughput Phenotyping of Morphological Seed and Fruit Characteristics Using X-Ray Computed Tomography

Traditional seed and fruit phenotyping are mainly accomplished by manual measurement or extraction of morphological properties from two-dimensional images. These methods are not only in low-throughput but also unable to collect their three-dimensional (3D) characteristics and internal morphology. X-ray computed tomography (CT) scanning, which provides a convenient means of non-destructively recording the external and internal 3D structures of seeds and fruits, offers a potential to overcome these limitations. However, the current CT equipment cannot be adopted to scan seeds and fruits with high throughput. And there is no specialized software for automatic extraction of phenotypes from CT images. Here, we introduced a high-throughput image acquisition approach by mounting a specially designed seed-fruit container onto the scanning bed. The corresponding 3D image analysis software, 3DPheno-Seed&Fruit, was created for automatic segmentation and rapid quantification of eight morphological phenotypes of internal and external compartments of seeds and fruits. 3DPheno-Seed&Fruit is a graphical user interface design and user-friendly software with an excellent phenotype result visualization function. We described the software in detail and benchmarked it based upon CT image analyses in seeds of soybean, wheat, peanut, pine nut, pistachio nut and dwarf Russian almond fruit. R 2 values between the extracted and manual measurements of seed length, width, thickness, and radius ranged from 0.80 to 0.96 for soybean and wheat. High correlations were found between the 2D (length, width, thickness, and radius) and 3D (volume and surface area) phenotypes for soybean. Overall, our methods provide robust and novel tools for phenotyping the morphological seed and fruit traits of various plant species, which could benefit crop breeding and functional genomics.

Effects of Rht17 in combination with Vrn-B1 and Ppd-D1 alleles on agronomic traits in wheat in black earth and non-black earth regions

BACKGROUND

Plant height is an important wheat trait that is regulated by multiple genes, among which Rht is of the utmost value. In wheat, Rht-B1p (=Rht17) is a mutant allele of the Rht gene that encodes for a DELLA-protein and results in the development of gibberellin-insensitive plants with a dwarfing phenotype. The pleiotropic effects of dwarfing genes on yield are highly dependent on both the genetic background and the environmental conditions. In Russia, the Central Non-Black Earth Region and Krasnodar Krai are two economically important regions that require differing management for sustainable wheat production for food, feed and industry. The purpose of our study was to compare the pleiotropic effects of Rht-B1p on the main valuable agronomic traits in the F3:4 families of the spring bread wheat Chris Mutant/Novosibirskaya 67 in the genetic background of Vrn-B1a/vrn-B1 (spring/winter phenotype) and Ppd-D1a/Ppd-D1b (insensitivity/sensitivity to photoperiod) alleles in a field experiment in Moscow and Krasnodar Krai.

RESULTS

Plant height was reduced on average by 21 cm (28%) and 25 cm (30%), respectively; Ppd-D1a slightly strengthened the dwarfing effect in Moscow and mitigated it in Krasnodar Krai. Grain weight of the main spike was reduced by Rht-B1p in Moscow and to lesser extent in Krasnodar; Ppd-D1a and Vrn-B1a tended to partially compensate for this loss in Krasnodar Krai. Thousand grain weight was reduced on average by 5.3 g (16%) and 2.9 g (10%) in Moscow and Krasnodar Krai, respectively, but was partially compensated for by Ppd-D1a in Krasnodar Krai. Harvest index was increased due to Rht-B1p by 6 and 10% in Moscow and Krasnodar Krai, respectively. Rht-B1p resulted in a delay of heading by 1-2 days in Moscow. Ppd-D1a accelerated heading by 1 day and 6 days in Moscow and in Krasnodar Krai, respectively.

CONCLUSIONS

Rht-B1p could be introduced into wheat breeding along with dwarfing genes such as Rht-B1b and Rht-D1b. Special attention should be paid to its combination with Ppd-D1a and Vrn-B1a as regulators of developmental rates, compensators of adverse effects of Rht-B1p on productivity and enhancers of positive effect of Rht-B1p on harvest index.

Quantifying Drosophila adults with the use of a smartphone

A method for automation of imago quantifying and fecundity assessment in Drosophila with the use of mobile devices running Android operating system is proposed. The traditional manual method of counting the progeny takes a long time and limits the opportunity of making large-scale experiments. Thus, the development of computerized methods that would allow us to automatically make a quantitative estimate of Drosophilamelanogaster fecundity is an urgent requirement. We offer a modification of the mobile application SeedCounter that analyzes images of objects placed on a standard sheet of paper for an automatic calculation of D. melanogaster offspring or quantification of adult flies in any other kind of experiment. The relative average error in estimates of the number of flies by mobile app is about 2% in comparison with the manual counting and the processing time is six times shorter. Study of the effects of imaging conditions on accuracy of flies counting showed that lighting conditions do not significantly affect this parameter, and higher accuracy can be achieved using high-resolution smartphone cameras (8 Mpx and more). These results indicate the high accuracy and efficiency of the method suggested.This article has an associated First Person interview with the first author of the paper.

Image-Based, Organ-Level Plant Phenotyping for Wheat Improvement

Wheat was one of the first grain crops domesticated by humans and remains among the major contributors to the global calorie and protein budget. The rapidly expanding world population demands further enhancement of yield and performance of wheat. Phenotypic information has historically been instrumental in wheat breeding for improved traits. In the last two decades, a steadily growing collection of tools and imaging software have given us the ability to quantify shoot, root, and seed traits with progressively increasing accuracy and throughput. This review discusses challenges and advancements in image analysis platforms for wheat phenotyping at the organ level. Perspectives on how these collective phenotypes can inform basic research on understanding wheat physiology and breeding for wheat improvement are also provided.

Phenotypic effects of the dwarfing gene Rht-17 in spring durum wheat under two climatic conditions

Alleles of the genes, conferring a dwarfing phenotype, play a crucial role in wheat breeding, as they not only reduce plant height, ensuring their resistance to lodging, but also have a number of positive and negative pleiotropic effects on plant productivity. Durum wheat carries only two subgenomes (A and B), which limits the use of the D-subgenome genes and requires the expansion of the arsenal of dwarfing alleles and the study of their effects on height and agronomically important traits. We studied the effect of the gibberellin-insensitive allele Rht-B1p in the B2F2:3 families, developed by crossing Chris Mutant /#517//LD222 in a field experiment in Moscow and Krasnodar. In our experiments, plants homozygous for Rht-B1p were shorter than those homozygous for the wild-type allele Rht-B1a by 36.3 cm (40 %) in Moscow and 49.5 cm (48 %) in Krasnodar. In the field experiment in Krasnodar, each plant with Rht-B1p had one less internode than any plant with Rht-B1a, which additionally contributed to the decrease in plant height. Grain weight per main spike was lower in plants with Rht-B1p than in plants with Rht-B1a by 12 % in Moscow and by 23 % in Krasnodar due to a decrease in 1000 grain weight in both regions of the field experiment. The number of grains per main spike in plants with Rht-B1p was higher in comparison to that with Rht-B1a by 6.5 % in Moscow due to an increase in spikelet number per main spike and by 11 % in Krasnodar due to an increase in grain number per spikelet. The onset of heading in plants with Rht-B1p in comparison with the plants with the wild-type allele Rht-B1a was 7 days later in Krasnodar. The possibility and prospects for the use of Rht-B1p in the breeding of durum wheat are discussed.

Overexpression of ca1pase Decreases Rubisco Abundance and Grain Yield in Wheat

Rubisco catalyzes the fixation of CO2 into organic compounds that are used for plant growth and the production of agricultural products, and specific sugar-phosphate derivatives bind tightly to the active sites of Rubisco, locking the enzyme in a catalytically inactive conformation. 2-carboxy-d-arabinitol-1-phosphate phosphatase (CA1Pase) dephosphorylates such tight-binding inhibitors, contributing to the maintenance of Rubisco activity. Here, we investigated the hypothesis that overexpressing ca1pase would decrease the abundance of Rubisco inhibitors, thereby increasing the activity of Rubisco and enhancing photosynthetic performance and productivity in wheat (Triticum aestivum). Plants of four independent wheat transgenic lines overexpressing ca1pase showed up to 30-fold increases in ca1pase expression compared to the wild type. Plants overexpressing ca1pase had lower numbers of Rubisco tight-binding inhibitors and higher Rubisco activation state than the wild type; however, there were 17% to 60% fewer Rubisco active sites in the four transgenic lines than in the wild type. The lower Rubisco content in plants overexpressing ca1pase resulted in lower initial and total carboxylating activities measured in flag leaves at the end of the vegetative stage and lower aboveground biomass and grain yield measured in fully mature plants. Hence, contrary to what would be expected, ca1pase overexpression decreased Rubisco content and compromised wheat grain yields. These results support a possible role for Rubisco inhibitors in protecting the enzyme and maintaining an adequate number of Rubisco active sites to support carboxylation rates in planta.

Image-based analysis of quantitative morphological characteristics of wild potato tubers using the desktop application SeedСounter

The development of quantitative digital phenotyping methods for evaluation of wild potato (section Petota Dumort., genus Solanum L.) tuberization is required for annotation of genebank collections and selection of the suitable donor material for potato breeding. There are no available methods specifically designed for the quantitative analysis of wild potato tuber morphology. The current study is devoted to evaluation of wild potato tubers’ morphological characteristics using a digital image processing technique. For this purpose, the mobile application SeedSounter developed previously for grain analysis was specifically adapted for tuber phenotyping. The application estimates the number and shape of objects scattered on a standard sheet of white paper (i. e. A3 or A4). Twelve accessions from the VIR genebank collection belonging to nine Petota species were grown in pots protected with garden fabric during the growing season of cultivated potato (Novosibirsk region). Tubers were collected form plants of nine genotypes. Three genotypes did not produce tubers. The weight of tubers collected from each plant was measured. The tuber yield from each plant was analyzed using SeedCounter (http://wheatdb.org/seedcounter). The number of tubers per plant was counted; the following characteristics were extracted from the images of individual tubers: length, width, projected area, length to width ratio, сircularity, roundness, rugosity and solidity. One-way ANOVA showed a significant effect of genotype on all measured characteristics. A pairwise comparison of nine Petota accessions using all measured parameters revealed statistically significant differences between 86 % of pairs. The overall tuber yield volume for each plant was  calculated as a sum of volumes of individual tubers; tuber volume was calculated from its length to width ratio and projected area. A strong correlation between the evaluated tuber yield volume and yield weight was shown. We propose tuber yield volume as a characteristic for a general evaluation of tuberization for wild potato, implementing the four-step scale from 0 to 3. According to this characteristic, the twelve wild potato accessions studied could be divided into four groups with different tuberization abilities. The evaluated tuberization ability is partially in accordance with previously obtained VIR data. The results presented demonstrate the possibility to use SeedCounter for  wild potato  collections phenotyping. 

Effect of Dwarfing Gene Ddw1 on Height and Agronomic Traits in Spring Triticale in Greenhouse and Field Experiments in a Non-Black Earth Region of Russia

Triticale is a relatively new crop which still possesses serious drawbacks that can be significantly improved by breeding. The dwarfing genes proved to be very useful in the development of new lodging resistant and productive cultivars of winter triticale. The aim of our research was to assess the effect of the Ddw1 dwarfing gene from rye on the agronomic valuable traits in spring triticale. The Ddw1 effect was studied in the greenhouse experiment in segregating the F_2:3 population and in the field of F_3:4 and F_4:5 families derived from crossing winter triticale ‘Hongor’ (Ddw1Ddw1) and spring triticale ‘Dublet’ (ddw1ddw1). As a result, in all three generations, a strong decrease in plant height was demonstrated that was accompanied by a decrease in grain weight per spike and 1000-grain weight. In field experiments, a decrease in spike length and increase in spike density and delay in flowering and heading were observed. As a result of decrease in culm vegetative weight due to Ddw1, the harvest index measured in F_4:5 increased. The spike fertility and number of grains were not affected by Ddw1. The comparison of Ddw1 in rye, winter, and spring triticale, and the possible role of Ddw1 in improving spring triticale are discussed.

What is cost-efficient phenotyping? Optimizing costs for different scenarios

Progress in remote sensing and robotic technologies decreases the hardware costs of phenotyping. Here, we first review cost-effective imaging devices and environmental sensors, and present a trade-off between investment and manpower costs. We then discuss the structure of costs in various real-world scenarios. Hand-held low-cost sensors are suitable for quick and infrequent plant diagnostic measurements. In experiments for genetic or agronomic analyses, (i) major costs arise from plant handling and manpower; (ii) the total costs per plant/microplot are similar in robotized platform or field experiments with drones, hand-held or robotized ground vehicles; (iii) the cost of vehicles carrying sensors represents only 5-26% of the total costs. These conclusions depend on the context, in particular for labor cost, the quantitative demand of phenotyping and the number of days available for phenotypic measurements due to climatic constraints. Data analysis represents 10-20% of total cost if pipelines have already been developed. A trade-off exists between the initial high cost of pipeline development and labor cost of manual operations. Overall, depending on the context and objsectives, "cost-effective" phenotyping may involve either low investment ("affordable phenotyping"), or initial high investments in sensors, vehicles and pipelines that result in higher quality and lower operational costs.

Plant Screen Mobile: an open-source mobile device app for plant trait analysis

BACKGROUND

The development of leaf area is one of the fundamental variables to quantify plant growth and physiological function and is therefore widely used to characterize genotypes and their interaction with the environment. To date, analysis of leaf area often requires elaborate and destructive measurements or imaging-based methods accompanied by automation that may result in costly solutions. Consequently in recent years there is an increasing trend towards simple and affordable sensor solutions and methodologies. A major focus is currently on harnessing the potential of applications developed for smartphones that provide access to analysis tools to a wide user basis. However, most existing applications entail significant manual effort during data acquisition and analysis.

RESULTS

With the development of Plant Screen Mobile we provide a suitable smartphone solution for estimating digital proxies of leaf area and biomass in various imaging scenarios in the lab, greenhouse and in the field. To distinguish between plant tissue and background the core of the application comprises different classification approaches that can be parametrized by users delivering results on-the-fly. We demonstrate the practical applications of computing projected leaf area based on two case studies with Eragrostis and Musa plants. These studies showed highly significant correlations with destructive measurements of leaf area and biomass from both ground truth measurements and estimations from well-established screening systems.

CONCLUSIONS

We show that a smartphone together with our analysis tool Plant Screen Mobile is a suitable platform for rapid quantification of leaf and shoot development of various plant architectures. Beyond the estimation of projected leaf area the app can also be used to quantify color and shape parameters of other plant material including seeds and flowers.

An Exploration of Deep-Learning Based Phenotypic Analysis to Detect Spike Regions in Field Conditions for UK Bread Wheat

Wheat is one of the major crops in the world, with a global demand expected to reach 850 million tons by 2050 that is clearly outpacing current supply. The continual pressure to sustain wheat yield due to the world's growing population under fluctuating climate conditions requires breeders to increase yield and yield stability across environments. We are working to integrate deep learning into field-based phenotypic analysis to assist breeders in this endeavour. We have utilised wheat images collected by distributed CropQuant phenotyping workstations deployed for multiyear field experiments of UK bread wheat varieties. Based on these image series, we have developed a deep-learning based analysis pipeline to segment spike regions from complicated backgrounds. As a first step towards robust measurement of key yield traits in the field, we present a promising approach that employ Fully Convolutional Network (FCN) to perform semantic segmentation of images to segment wheat spike regions. We also demonstrate the benefits of transfer learning through the use of parameters obtained from other image datasets. We found that the FCN architecture had achieved a Mean classification Accuracy (MA) >82% on validation data and >76% on test data and Mean Intersection over Union value (MIoU) >73% on validation data and and >64% on test datasets. Through this phenomics research, we trust our attempt is likely to form a sound foundation for extracting key yield-related traits such as spikes per unit area and spikelet number per spike, which can be used to assist yield-focused wheat breeding objectives in near future.

GainTKW: A Measurement System of Thousand Kernel Weight Based on the Android Platform

Thousand kernel weight (TKW) is an important parameter for the evaluation of grain yield. The traditional measurement method relies on manual steps: weighing and counting. In this paper, we developed a system for the automated evaluation of thousand kernel weight that combines a weighing module and Android devices, called “gainTKW”. The system is able to collect the weight information from the weighing module through a serial port using the RS232-micro USB cable. In the imaging process, we adopt a k-means clustering segmentation algorithm to solve the problem of uneven lighting. We used the marker-controlled watershed algorithm and area threshold method to count the number of kernels that are touching one another. These algorithms were implemented based on the OpenCV (Open Source Computer Vision) libraries. The system tested kernel images of six species taken with the Android device under different lighting conditions. The algorithms in this study can solve the segmentation problems caused by shadows, as well. The appropriate numbers of kernels, of different species, are counted with an error ratio upper limit of 3%. The application is convenient and easy to operate. For the experiments, we can prove the efficiency and accuracy of the developed system by comparing the results between the manual method and the proposed application.

A method to calculate the number of wheat seedlings in the 1st to the 3rd leaf growth stages

BACKGROUND

The number of cultivated wheat seedlings per unit area allows calculation of plant density. Wheat seedling density provides emergence data and this is useful for improving crop management. The number of wheat seedlings is typically determined by visual counts but this is time-consuming and laborious.

RESULTS

We obtained field digital images of 1st to 3rd leaf stage wheat seedlings. The seedlings were extracted using an image analysis technique that calculated the coverage degree of the seedlings and the number of angular points of overlapping leaves. The wheat seedling quantity estimation model was constructed using multivariate regression analysis. The model parameters included coverage degree, number of angular points, variety coefficient, and leaf age. Introduction of the number of angular points increased the accuracy of the single coverage degree model. The R² value was consistently > 0.95 when the model was applied to different varieties, indicating that the model was adaptable for different varieties. As the leaf stage or density increased, the accuracy of the model declined, but the minimum R² remained > 0.87, indicating good adaptability of the model to seedlings with different leaf ages and densities.

CONCLUSIONS

This method is an effective means for counting wheat seedlings in the 1st to the 3rd leaf stages.