Automated In Situ Seed Variety Identification via Deep Learning: A Case Study in Chickpea

Research Progress of Spectral Imaging Techniques in Plant Phenotype Studies

Spectral imaging technique has been widely applied in plant phenotype analysis to improve plant trait selection and genetic advantages. The latest developments and applications of various optical imaging techniques in plant phenotypes were reviewed, and their advantages and applicability were compared. X-ray computed tomography (X-ray CT) and light detection and ranging (LiDAR) are more suitable for the three-dimensional reconstruction of plant surfaces, tissues, and organs. Chlorophyll fluorescence imaging (ChlF) and thermal imaging (TI) can be used to measure the physiological phenotype characteristics of plants. Specific symptoms caused by nutrient deficiency can be detected by hyperspectral and multispectral imaging, LiDAR, and ChlF. Future plant phenotype research based on spectral imaging can be more closely integrated with plant physiological processes. It can more effectively support the research in related disciplines, such as metabolomics and genomics, and focus on micro-scale activities, such as oxygen transport and intercellular chlorophyll transmission.

Detection and identification of plant leaf diseases using YOLOv4

Detecting plant leaf diseases accurately and promptly is essential for reducing economic consequences and maximizing crop yield. However, farmers' dependence on conventional manual techniques presents a difficulty in accurately pinpointing particular diseases. This research investigates the utilization of the YOLOv4 algorithm for detecting and identifying plant leaf diseases. This study uses the comprehensive Plant Village Dataset, which includes over fifty thousand photos of healthy and diseased plant leaves from fourteen different species, to develop advanced disease prediction systems in agriculture. Data augmentation techniques including histogram equalization and horizontal flip were used to improve the dataset and strengthen the model's resilience. A comprehensive assessment of the YOLOv4 algorithm was conducted, which involved comparing its performance with established target identification methods including Densenet, Alexanet, and neural networks. When YOLOv4 was used on the Plant Village dataset, it achieved an impressive accuracy of 99.99%. The evaluation criteria, including accuracy, precision, recall, and f1-score, consistently showed high performance with a value of 0.99, confirming the effectiveness of the proposed methodology. This study's results demonstrate substantial advancements in plant disease detection and underscore the capabilities of YOLOv4 as a sophisticated tool for accurate disease prediction. These developments have significant significance for everyone involved in agriculture, researchers, and farmers, providing improved capacities for disease control and crop protection.

Artificial neural network approach for predicting the sesame (Sesamum indicum L.) leaf area: A non-destructive and accurate method

The estimative of the leaf area using a nondestructive method is paramount for successive evaluations in the same plant with precision and speed, not requiring high-cost equipment. Thus, the objective of this work was to construct models to estimate leaf area using artificial neural network models (ANN) and regression and to compare which model is the most effective model for predicting leaf area in sesame culture. A total of 11,000 leaves of four sesame cultivars were collected. Then, the length (L) and leaf width (W), and the actual leaf area (LA) were quantified. For the ANN model, the parameters of the length and width of the leaf were used as input variables of the network, with hidden layers and leaf area as the desired output parameter. For the linear regression models, leaf dimensions were considered independent variables, and the actual leaf area was the dependent variable. The criteria for choosing the best models were: the lowest root of the mean squared error (RMSE), mean absolute error (MAE), and absolute mean percentage error (MAPE), and higher coefficients of determination (R²). Among the linear regression models, the equation yˆ=0.515+0.584*LW was considered the most indicated to estimate the leaf area of the sesame. In modeling with ANNs, the best results were found for model 2-3-1, with two input variables (L and W), three hidden variables, and an output variable (LA). The ANN model was more accurate than the regression models, recording the lowest errors and higher R² in the training phase (RMSE: 0.0040; MAE: 0.0027; MAPE: 0.0587; and R²: 0.9834) and in the test phase (RMSE: 0.0106; MAE: 0.0029; MAPE: 0.0611; and R²: 0.9828). Thus, the ANN method is the most indicated and accurate for predicting the leaf area of the sesame.

A Deep Learning Image System for Classifying High Oleic Sunflower Seed Varieties

Sunflower seeds, one of the main oilseeds produced around the world, are widely used in the food industry. Mixtures of seed varieties can occur throughout the supply chain. Intermediaries and the food industry need to identify the varieties to produce high-quality products. Considering that high oleic oilseed varieties are similar, a computer-based system to classify varieties could be useful to the food industry. The objective of our study is to examine the capacity of deep learning (DL) algorithms to classify sunflower seeds. An image acquisition system, with controlled lighting and a Nikon camera in a fixed position, was constructed to take photos of 6000 seeds of six sunflower seed varieties. Images were used to create datasets for training, validation, and testing of the system. A CNN AlexNet model was implemented to perform variety classification, specifically classifying from two to six varieties. The classification model reached an accuracy value of 100% for two classes and 89.5% for the six classes. These values can be considered acceptable, because the varieties classified are very similar, and they can hardly be classified with the naked eye. This result proves that DL algorithms can be useful for classifying high oleic sunflower seeds.

Near-infrared hyperspectral imaging for online measurement of the viability detection of naturally aged watermelon seeds

The viability status of seeds before sowing is important to farmers as it allows them to make yield predictions. Monitoring the seed quality in a rapid and nondestructive manner may create a perfect solution, especially for industrial sorting applications. However, current offline laboratory-based strategies employed for the monitoring of seed viability are time-consuming and thus cannot satisfy industrial needs where there is a substantial number of seeds to be analyzed. In this study, we describe a prototype online near-infrared (NIR) hyperspectral imaging system that can be used for the rapid detection of seed viability. A wavelength range of 900-1700 nm was employed to obtain spectral images of three different varieties of naturally aged watermelon seed samples. The partial least square discriminant analysis (PLS-DA) model was employed for real-time viability prediction for seed samples moving through a conveyor unit at a speed of 49 mm/sec. A suction unit was further incorporated to develop the online system and it was programmatically controlled to separate the detected viable seeds from nonviable ones. For an external validation sample set showed classification accuracy levels of 91.8%, 80.7%, and 77.8% in relation to viability for the three varieties of watermelon seed with healthy seedling growth. The regression coefficients of the classification model distinguished some chemical differences in viable and nonviable seed which was verified by the chromatographic analysis after the detection of the proposed online system. The results demonstrated that the developed online system with the viability prediction model has the potential to be used in the seed industry for the quality monitoring of seeds.

Leaf Count Aided Novel Framework for Rice (Oryza sativa L.) Genotypes Discrimination in Phenomics: Leveraging Computer Vision and Deep Learning Applications

Drought is a detrimental factor to gaining higher yields in rice (Oryza sativa L.), especially amid the rising occurrence of drought across the globe. To combat this situation, it is essential to develop novel drought-resilient varieties. Therefore, screening of drought-adaptive genotypes is required with high precision and high throughput. In contemporary emerging science, high throughput plant phenotyping (HTPP) is a crucial technology that attempts to break the bottleneck of traditional phenotyping. In traditional phenotyping, screening significant genotypes is a tedious task and prone to human error while measuring various plant traits. In contrast, owing to the potential advantage of HTPP over traditional phenotyping, image-based traits, also known as i-traits, were used in our study to discriminate 110 genotypes grown for genome-wide association study experiments under controlled (well-watered), and drought-stress (limited water) conditions, under a phenomics experiment in a controlled environment with RGB images. Our proposed framework non-destructively estimated drought-adaptive plant traits from the images, such as the number of leaves, convex hull, plant-aspect ratio (plant spread), and similarly associated geometrical and morphological traits for analyzing and discriminating genotypes. The results showed that a single trait, the number of leaves, can also be used for discriminating genotypes. This critical drought-adaptive trait was associated with plant size, architecture, and biomass. In this work, the number of leaves and other characteristics were estimated non-destructively from top view images of the rice plant for each genotype. The estimation of the number of leaves for each rice plant was conducted with the deep learning model, YOLO (You Only Look Once). The leaves were counted by detecting corresponding visible leaf tips in the rice plant. The detection accuracy was 86-92% for dense to moderate spread large plants, and 98% for sparse spread small plants. With this framework, the susceptible genotypes (MTU1010, PUSA-1121 and similar genotypes) and drought-resistant genotypes (Heera, Anjali, Dular and similar genotypes) were grouped in the core set with a respective group of drought-susceptible and drought-tolerant genotypes based on the number of leaves, and the leaves' emergence during the peak drought-stress period. Moreover, it was found that the number of leaves was significantly associated with other pertinent morphological, physiological and geometrical traits. Other geometrical traits were measured from the RGB images with the help of computer vision.

Hyperspectral Monitoring of Powdery Mildew Disease Severity in Wheat Based on Machine Learning

Powdery mildew has a negative impact on wheat growth and restricts yield formation. Therefore, accurate monitoring of the disease is of great significance for the prevention and control of powdery mildew to protect world food security. The canopy spectral reflectance was obtained using a ground feature hyperspectrometer during the flowering and filling periods of wheat, and then the Savitzky-Golay method was used to smooth the measured spectral data, and as original reflectivity (OR). Firstly, the OR was spectrally transformed using the mean centralization (MC), multivariate scattering correction (MSC), and standard normal variate transform (SNV) methods. Secondly, the feature bands of above four transformed spectral data were extracted through a combination of the Competitive Adaptive Reweighted Sampling (CARS) and Successive Projections Algorithm (SPA) algorithms. Finally, partial least square regression (PLSR), support vector regression (SVR), and random forest regression (RFR) were used to construct an optimal monitoring model for wheat powdery mildew disease index (mean disease index, mDI). The results showed that after Pearson correlation, two-band optimization combinations and machine learning method modeling comparisons, the comprehensive performance of the MC spectrum data was the best, and it was a better method for pretreating disease spectrum data. The transformed spectral data combined with the CARS-SPA algorithm was able to extract the characteristic bands more effectively. The number of bands screened was more than the number of bands extracted by the OR data, and the band positions were more evenly distributed. In comparison of different machine learning modeling methods, the RFR model performed the best (coefficient of determination, R ² = 0.741-0.852), while the SVR and PLSR models performed similarly (R ² = 0.733-0.836). Taken together, the estimation accuracy of spectral data transformation using the MC method combined with the RFR model (MC-RFR) was the highest, the model R ² was 0.849-0.852, and the root mean square error (RMSE) and the mean absolute error (MAE) ranged from 2.084 to 2.177 and 1.684 to 1.777, respectively. Compared with the OR combined with the RFR model (OR-RFR), the R ² increased by 14.39%, and the R ² of RMSE and MAE decreased by 23.9 and 27.87%. Also, the monitoring accuracy of flowering stage is better than that of grain filling stage, which is due to the relative stability of canopy structure in flowering stage. It can be seen that without changing the shape of the spectral curve, and that the use of MC to preprocess spectral data, the use of CARS and SPA algorithms to extract characteristic bands, and the use of RFR modeling methods to enhance the synergy between multiple variables, and the established model (MC-CARS-SPA-RFR) can better extract the covariant relationship between the canopy spectrum and the disease, thereby improving the monitoring accuracy of wheat powdery mildew. The research results of this study provide ideas and methods for realizing high-precision remote sensing monitoring of crop disease status.

A Hyperspectral Data 3D Convolutional Neural Network Classification Model for Diagnosis of Gray Mold Disease in Strawberry Leaves

Gray mold disease is one of the most frequently occurring diseases in strawberries. Given that it spreads rapidly, rapid countermeasures are necessary through the development of early diagnosis technology. In this study, hyperspectral images of strawberry leaves that were inoculated with gray mold fungus to cause disease were taken; these images were classified into healthy and infected areas as seen by the naked eye. The areas where the infection spread after time elapsed were classified as the asymptomatic class. Square regions of interest (ROIs) with a dimensionality of 16 × 16 × 150 were acquired as training data, including infected, asymptomatic, and healthy areas. Then, 2D and 3D data were used in the development of a convolutional neural network (CNN) classification model. An effective wavelength analysis was performed before the development of the CNN model. Further, the classification model that was developed with 2D training data showed a classification accuracy of 0.74, while the model that used 3D data acquired an accuracy of 0.84; this indicated that the 3D data produced slightly better performance. When performing classification between healthy and asymptomatic areas for developing early diagnosis technology, the two CNN models showed a classification accuracy of 0.73 with regards to the asymptomatic ones. To increase accuracy in classifying asymptomatic areas, a model was developed by smoothing the spectrum data and expanding the first and second derivatives; the results showed that it was possible to increase the asymptomatic classification accuracy to 0.77 and reduce the misclassification of asymptomatic areas as healthy areas. Based on these results, it is concluded that the proposed 3D CNN classification model can be used as an early diagnosis sensor of gray mold diseases since it produces immediate on-site analysis results of hyperspectral images of leaves.

Detection Method of Citrus Psyllids With Field High-Definition Camera Based on Improved Cascade Region-Based Convolution Neural Networks

Citrus psyllid is the only insect vector of citrus Huanglongbing (HLB), which is the most destructive disease in the citrus industry. There is no effective treatment for HLB, so detecting citrus psyllids as soon as possible is the key prevention measure for citrus HLB. It is time-consuming and laborious to search for citrus psyllids through artificial patrol, which is inconvenient for the management of citrus orchards. With the development of artificial intelligence technology, a computer vision method instead of the artificial patrol can be adopted for orchard management to reduce the cost and time. The citrus psyllid is small in shape and gray in color, similar to the stem, stump, and withered part of the leaves, leading to difficulty for the traditional target detection algorithm to achieve a good recognition effect. In this work, in order to make the model have good generalization ability under outdoor light condition, a high-definition camera to collect data set of citrus psyllids and citrus fruit flies under natural light condition was used, a method to increase the number of small target pests in citrus based on semantic segmentation algorithm was proposed, and the cascade region-based convolution neural networks (R-CNN) (convolutional neural network) algorithm was improved to enhance the recognition effect of small target pests using multiscale training, combining CBAM attention mechanism with high-resolution feature retention network high-resoultion network (HRNet) as feature extraction network, adding sawtooth atrous spatial pyramid pooling (ASPP) structure to fully extract high-resolution features from different scales, and adding feature pyramid networks (FPN) structure for feature fusion at different scales. To mine difficult samples more deeply, an online hard sample mining strategy was adopted in the process of model sampling. The results show that the improved cascade R-CNN algorithm after training has an average recognition accuracy of 88.78% for citrus psyllids. Compared with VGG16, ResNet50, and other common networks, the improved small target recognition algorithm obtains the highest recognition performance. Experimental results also show that the improved cascade R-CNN algorithm not only performs well in citrus psylla identification but also in other small targets such as citrus fruit flies, which makes it possible and feasible to detect small target pests with a field high-definition camera.

An Approach Using Emerging Optical Technologies and Artificial Intelligence Brings New Markers to Evaluate Peanut Seed Quality

Seeds of high physiological quality are defined by their superior germination capacity and uniform seedling establishment. Here, it was investigated whether multispectral images combined with machine learning models can efficiently categorize the quality of peanut seedlots. The seed quality from seven lots was assessed traditionally (seed weight, water content, germination, and vigor) and by multispectral images (area, length, width, brightness, chlorophyll fluorescence, anthocyanin, and reflectance: 365 to 970 nm). Seedlings from the seeds of each lot were evaluated for their photosynthetic capacity (fluorescence and chlorophyll index, F₀, F_m, and F_v/F_m) and stress indices (anthocyanin and NDVI). Artificial intelligence features (QDA method) applied to the data extracted from the seed images categorized lots with high and low quality. Higher levels of anthocyanin were found in the leaves of seedlings from low quality seeds. Therefore, this information is promising since the initial behavior of the seedlings reflected the quality of the seeds. The existence of new markers that effectively screen peanut seed quality was confirmed. The combination of physical properties (area, length, width, and coat brightness), pigments (chlorophyll fluorescence and anthocyanin), and light reflectance (660, 690, and 780 nm), is highly efficient to identify peanut seedlots with superior quality (98% accuracy).

Citrus Huanglongbing Detection Based on Multi-Modal Feature Fusion Learning

Citrus Huanglongbing (HLB), also named citrus greening disease, occurs worldwide and is known as a citrus cancer without an effective treatment. The symptoms of HLB are similar to those of nutritional deficiency or other disease. The methods based on single-source information, such as RGB images or hyperspectral data, are not able to achieve great detection performance. In this study, a multi-modal feature fusion network, combining a RGB image network and hyperspectral band extraction network, was proposed to recognize HLB from four categories (HLB, suspected HLB, Zn-deficient, and healthy). Three contributions including a dimension-reduction scheme for hyperspectral data based on a soft attention mechanism, a feature fusion proposal based on a bilinear fusion method, and auxiliary classifiers to extract more useful information are introduced in this manuscript. The multi-modal feature fusion network can effectively classify the above four types of citrus leaves and is better than single-modal classifiers. In experiments, the highest accuracy of multi-modal network recognition was 97.89% when the amount of data was not very abundant (1,325 images of the four aforementioned types and 1,325 pieces of hyperspectral data), while the single-modal network with RGB images only achieved 87.98% recognition and the single-modal network using hyperspectral information only 89%. Results show that the proposed multi-modal network implementing the concept of multi-source information fusion provides a better way to detect citrus HLB and citrus deficiency.

DBA_SSD: A Novel End-to-End Object Detection Algorithm Applied to Plant Disease Detection

In response to the difficulty of plant leaf disease detection and classification, this study proposes a novel plant leaf disease detection method called deep block attention SSD (DBA_SSD) for disease identification and disease degree classification of plant leaves. We propose three plant leaf detection methods, namely, squeeze-and-excitation SSD (Se_SSD), deep block SSD (DB_SSD), and DBA_SSD. Se_SSD fuses SSD feature extraction network and attention mechanism channel, DB_SSD improves VGG feature extraction network, and DBA_SSD fuses the improved VGG network and channel attention mechanism. To reduce the training time and accelerate the training process, the convolutional layers trained in the Image Net image dataset by the VGG model are migrated to this model, whereas the collected plant leaves disease image dataset is randomly divided into training set, validation set, and test set in the ratio of 8:1:1. We chose the PlantVillage dataset after careful consideration because it contains images related to the domain of interest. This dataset consists of images of 14 plants, including images of apples, tomatoes, strawberries, peppers, and potatoes, as well as the leaves of other plants. In addition, data enhancement methods, such as histogram equalization and horizontal flip were used to expand the image data. The performance of the three improved algorithms is compared and analyzed in the same environment and with the classical target detection algorithms YOLOv4, YOLOv3, Faster RCNN, and YOLOv4 tiny. Experiments show that DBA_SSD outperforms the two other improved algorithms, and its performance in comparative analysis is superior to other target detection algorithms.

Meta-Learning for Few-Shot Plant Disease Detection

Plant diseases can harm crop growth, and the crop production has a deep impact on food. Although the existing works adopt Convolutional Neural Networks (CNNs) to detect plant diseases such as Apple Scab and Squash Powdery mildew, those methods have limitations as they rely on a large amount of manually labeled data. Collecting enough labeled data is not often the case in practice because: plant pathogens are variable and farm environments make collecting data difficulty. Methods based on deep learning suffer from low accuracy and confidence when facing few-shot samples. In this paper, we propose local feature matching conditional neural adaptive processes (LFM-CNAPS) based on meta-learning that aims at detecting plant diseases of unseen categories with only a few annotated examples, and visualize input regions that are ‘important’ for predictions. To train our network, we contribute Miniplantdisease-Dataset that contains 26 plant species and 60 plant diseases. Comprehensive experiments demonstrate that our proposed LFM-CNAPS method outperforms the existing methods.