Search

This study was conducted on Xanthomonas axonopodis pv, which causes significant economic losses in the agricultural sector. Here, we study a common bacterial blight disease caused by the phaseoli (XaP) bacterial pathogen on Üstün42 and Akbulut bean genera. In this study, a total of 4000 images, healthy and diseased, were used for both bean breeds. These images were classified by AlexNet, VGG16, and VGG19 models. Later, reclassification was performed by applying pre-processing to the raw images. According to the results obtained, the accuracy rates of the pre-processed images classified by the VGG19, VGG16 and AlexNet models were determined as 0.9213, 0.9125 and 0.8950, respectively. The models were then hybridized with LSTM and BiLSTM for raw and pre-processed images and new models were created. When the performance of these hybrid models was evaluated, it was found that the models hybridized with LSTM were more successful than the simple models, while the models hybridized with BiLSTM gave better results than the models hybridized with LSTM. In particular, the VGG19+BiLSTM model attracted attention by achieving 94.25% classification accuracy with pre-processed images. This study emphasizes the effectiveness of image processing techniques in agriculture in the field of disease detection and is important as a new dataset in the literature for evaluating the performance of hybridized models. [ABSTRACT FROM AUTHOR]

The significance of environmental considerations has been highlighted by the substantial impact of plant pests on ecosystems. Addressing the urgent demand for sophisticated pest management solutions in arboreal environments, this study leverages advanced deep learning technologies to accurately detect and classify common tree pests, such as "mole cricket", "aphids", and "Therioaphis maculata (Buckton)". Through comparative analysis with the baseline model ResNet-18 model, this research not only enhances the SE-RegNetY and SE-RegNet models but also introduces innovative frameworks, including GCT-Inception-ResNet-V3, SE-Inception-ResNet-V3, and SE-Inception-RegNetY-V3 models. Notably, the GCT-Inception-ResNet-V3 model demonstrates exceptional performance, achieving a remarkable average overall accuracy of 94.59%, average kappa coefficient of 91.90%, average mAcc of 94.60%, and average mIoU of 89.80%. These results signify substantial progress over conventional methods, outperforming the baseline model's results by margins of 9.1%, nearly 13.7%, 9.1%, and almost 15% in overall accuracy, kappa coefficient, mAcc, and mIoU, respectively. This study signifies a considerable step forward in blending sustainable agricultural practices with environmental conservation, setting new benchmarks in agricultural pest management. By enhancing the accuracy of pest identification and classification in agriculture, it lays the groundwork for more sustainable and eco-friendly pest control approaches, offering valuable contributions to the future of agricultural protection. [ABSTRACT FROM AUTHOR]

Nowadays, many image processing and machine learning (ML) methods are used in mango-quality classification systems. Existing algorithms perform independently to capture the relationships between features in the dataset. Nevertheless, each method has its advantages and disadvantages. As a result, this study presents an ensemble-learning framework that combines the strengths of multiple ML algorithms to make predictions. Initially, different image processing algorithms are used to extract external mango features. Next, the dataset is constructed by combining those features with weight values from sensor signals. Following that, different ML algorithms are evaluated on the dataset to determine which ones are robust. Subsequently, various ensemble-learning approaches are deployed, such as bagging, boosting, and stacking. Finally, those models are evaluated and compared, to decide which model is suited for this study's dataset. In the experimental part, the assessment of errors demonstrates the usefulness of image processing algorithms. Furthermore, evaluation of the training models revealed that the stacking model, which integrates several methods in both the base learner and meta-learner, produced the highest results in precision, recall, F1-score, and accuracy, with values of 0.9855, 0.9901, 0.9876, and 0.9863, respectively. These experimental results confirm the robustness of the proposed methodologies for classifying mango quality. [ABSTRACT FROM AUTHOR]

Rice lodging is a crucial problem in rice production. Lodging during growing and harvesting periods can decrease rice yields. Practical lodging judgment for rice can provide effective reference information for yield prediction and harvesting. This article proposes a binocular camera-based lodging judgment method for rice in real-time. As a first step, the binocular camera and Inertial Measurement Unit (IMU) were calibrated. Secondly, Census and Grayscale Level cost features are constructed for stereo matching of left and right images. The Cross-Matching Cost Aggregation method is improved to compute the aggregation space in the LAB color space. Then, the Winner-Takes-All algorithm is applied to determine the optimal disparity for each pixel. A disparity map is constructed, and Multi-Step Disparity Refinement is applied to the disparity map to generate the final one. Finally, coordinate transformation obtains 3D world coordinates corresponding to pixels. IMU calculates the real-time pose of the binocular camera. A pose transformation is applied to the 3D world coordinates of the rice to obtain its 3D world coordinates in the horizontal state of the camera (pitch and roll angles are equal to 0). Based on the distance between the rice and the camera level, thresholding was used to determine whether the region to be detected belonged to lodging rice. The disparity map effect of the proposed matching algorithm was tested on the Middlebury Benchmark v3 dataset. The results show that the proposed algorithm is superior to the widely used Semi-Global Block Matching (SGBM) stereo-matching algorithm. Field images of rice were analyzed for lodging judgments. After the threshold judgment, the lodging region results were accurate and could be used to judge rice lodging. By combining the algorithms with binocular cameras, the research results can provide practical technical support for yield estimation and intelligent control of rice harvesters. [ABSTRACT FROM AUTHOR]

Deep-learning-based methods for plant disease recognition pose challenges due to their high number of network parameters, extensive computational requirements, and overall complexity. To address this issue, we propose an improved residual-network-based multi-plant disease recognition method that combines the characteristics of plant diseases. Our approach introduces a lightweight technique called maximum grouping convolution to the ResNet18 model. We made three enhancements to adapt this method to the characteristics of plant diseases and ultimately reduced the convolution kernel requirements, resulting in the final model, Model_Lite. The experimental dataset comprises 20 types of plant diseases, including 13 selected from the publicly available Plant Village dataset and seven self-constructed images of apple leaves with complex backgrounds containing disease symptoms. The experimental results demonstrated that our improved network model, Model_Lite, contains only about 1/344th of the parameters and requires 1/35th of the computational effort compared to the original ResNet18 model, with a marginal decrease in the average accuracy of only 0.34%. Comparing Model_Lite with MobileNet, ShuffleNet, SqueezeNet, and GhostNet, our proposed Model_Lite model achieved a superior average recognition accuracy while maintaining a much smaller number of parameters and computational requirements than the above models. Thus, the Model_Lite model holds significant potential for widespread application in plant disease recognition and can serve as a valuable reference for future research on lightweight network model design. [ABSTRACT FROM AUTHOR]

The significance of environmental considerations has been highlighted by the substantial impact of plant pests on ecosystems. Addressing the urgent demand for sophisticated pest management solutions in arboreal environments, this study leverages advanced deep learning technologies to accurately detect and classify common tree pests, such as “mole cricket”, “aphids”, and “Therioaphis maculata (Buckton)”. Through comparative analysis with the baseline model ResNet-18 model, this research not only enhances the SE-RegNetY and SE-RegNet models but also introduces innovative frameworks, including GCT-Inception-ResNet-V3, SE-Inception-ResNet-V3, and SE-Inception-RegNetY-V3 models. Notably, the GCT-Inception-ResNet-V3 model demonstrates exceptional performance, achieving a remarkable average overall accuracy of 94.59%, average kappa coefficient of 91.90%, average mAcc of 94.60%, and average mIoU of 89.80%. These results signify substantial progress over conventional methods, outperforming the baseline model’s results by margins of 9.1%, nearly 13.7%, 9.1%, and almost 15% in overall accuracy, kappa coefficient, mAcc, and mIoU, respectively. This study signifies a considerable step forward in blending sustainable agricultural practices with environmental conservation, setting new benchmarks in agricultural pest management. By enhancing the accuracy of pest identification and classification in agriculture, it lays the groundwork for more sustainable and eco-friendly pest control approaches, offering valuable contributions to the future of agricultural protection.

Crop fungal diseases are a major threat to crop health and food security worldwide. The epidemiology is the basis for effective and sustainable control of crop fungal diseases. Safe, effective, sustainable, and eco-friendly disease control measures have important economic, ecological, and social significances. This Special Issue, "Epidemiology and Control of Fungal Diseases of Crop Plants", collected one communication and nine original research articles focusing on the identification and detection of the causal agents of alfalfa Fusarium root rot, strawberry black spot, and barley leaf stripe; the semantic segmentation of wheat stripe rust images; the image-based identification of wheat stripe rust and wheat leaf rust; the image-based identification of the severity of wheat Fusarium head blight; the development process of vanilla Fusarium wilt; the regional migration of wheat leaf rust pathogen; the early prediction of potato early blight; the screening of alternative fungicides for the control of alfalfa Fusarium root rot; and the biocontrol potential of endophytic fungi to control of cumin root rot, presenting the progress of research on the epidemiology and control of crop fungal diseases. The studies contained in this Special Issue facilitated the development of epidemiology of the related crop fungal diseases and provided some basis for control of the diseases, which is conducive to the sustainable management of these diseases. [ABSTRACT FROM AUTHOR]

Harvesting is an important procedure for hydroponic lettuces in plant factories. At present, hydroponic lettuces are mainly harvested manually, and the key difficulty in mechanical harvesting is reducing the occurrence of leaf injury. Measuring the size of hydroponic lettuces using the image processing method and intelligently adjusting the operating parameters of the harvesting device are the foundation of high-quality harvesting for lettuces. The overlapped leaves of adjacent hydroponic lettuces cause difficulties in measuring lettuce size, especially the leaves expansion size. Therefore, we proposed an image processing method for measuring lettuce height and leaves expansion size according to the upper contour feature of lettuces and an image included three lettuces. Firstly, the upper contours of the lettuces were extracted and segmented via image preprocessing. Secondly, lettuce height was measured according to the maximum ordinate of the contour. Lastly, the lettuce's upper contour was fitted to a function to measure the leaves expansion size. The measurement results showed that the maximal relative error of the lettuce height measurements was 5.58%, and the average was 2.14%. The effect of the quadratic function in fitting the upper contour was the best compared with the cubic function and sine function. The maximal relative error of the leaves expansion size measurements was 8.59%, and the average was 4.03%. According to the results of the lettuce height and leaves expansion size measurements, the grabbing parameters of each lettuce were intelligently adjusted to verify the harvesting effect. The harvesting success rates of lettuces was above 90%, and the injured leaves areas of the left, middle, and right lettuces in each image were 192.6 mm2, 228.1 mm2, and 205.6 mm2, respectively. This paper provides a reference for the design and improvement of intelligent harvesters for hydroponic lettuces. [ABSTRACT FROM AUTHOR]

Rice production has faced numerous challenges in recent years, and traditional methods are still being used to detect rice diseases. This research project developed an automated rice blast disease diagnosis technique based on deep learning, image processing, and transfer learning with pre-trained models such as Inception V3, VGG16, VGG19, and ResNet50. The public dataset consists of 2000 images; about 1200 images belong to the leaf blast class, and 800 to the healthy leaf class. The modified connection-skipping ResNet 50 had the highest accuracy of 99.75% with a loss rate of 0.33, while the other models achieved 98.16%, 98.47%, and 98.56%, respectively. Furthermore, ResNet 50 achieved a validation accuracy of 99.69%, precision of 99.50%, F1-score of 99.70, and AUC of 99.83%. In conclusion, the study demonstrated a superior performance and disease prediction using the Gradio web application. [ABSTRACT FROM AUTHOR]

In the U.S., peanut farmers receive premium prices for crops with high seed grades. One component of seed grade is the proportion of seed weight to that of pod hulls and other matter. Seed weight and size are also important traits for food processors. Current methods for evaluating peanut seed grade require the opening of the pod and are time-consuming and labor-intensive. In this study, a non-destructive and efficient method to determine peanut seed weights was investigated. X-ray images of a total of 513 peanut pods from three commercial cultivars, each representing three market types, were taken using a soft X-ray imaging system. The region of interest of each image, the seeds, was extracted two ways, manually and with a differential evolution segmentation algorithm. The comprehensive attenuation index (CAI) value was calculated from the segmented regions of interest. Lastly, linear regression models were established between peanut seed weights and the CAI. The results demonstrated that the X-ray imaging technology, coupled with the differential evolution segmentation algorithm, may be used to estimate seed weights efficiently from intact peanut pods. [ABSTRACT FROM AUTHOR]

Rice-fish cultivation, also known as Manipadi in Indonesia, is one of the many integrated farming systems where fish are grown concurrently with rice. However, this integrated system needs to be optimized by organic fertilizer. The application of organic fertilizers, such as compost and local biofertilizers, when implemented into this integrated system, can optimize the yield per land for both rice and fish. However, this combination must be evaluated systematically by multiple evaluation criteria and statistical analyses. Therefore, this study aimed to identify the combination of compost doses and/or local liquid organic fertilizer concentrations, based on multiple evaluation criteria, that supports the productivity of rice-fish integration agriculture. The experiment was carried out in the Wanuae farmer group of the Barebbo District, Bone Regency, Indonesia, between September 2018 and January 2019. The experiment employed a split plot design with a randomized complete block design (RCBD). The main plot consisted of compost (four levels), and the subplot was the local biofertilizer source (four levels). The results demonstrated that the number of fill grains was significantly affected by the compost treatment and the type of local biofiller. The effect of the compost dosing was more dominant in comparison with the local liquid organic fertilizer character and its interactions. A compost dosage of four tons ha−1 and a local liquid organic fertilizer, sourced from soaked coconut fiber with cow urine, has been recommended as the combination treatment to optimize the rice and fish yield potential. The Minapadi (rice fish) with additional high composting effectively increased the farmer's outcome with a 2-point R/C ratio, more so than those without composting. Moreover, the compost dosage in this Minapadi study requires further exploration for a better understanding. [ABSTRACT FROM AUTHOR]

The differentiation between the main crop and weeds is an important step for selective spraying systems to avoid agrochemical waste and reduce economic and environmental impacts. In this sense, this study aims to classify and map the area occupied by weeds, determine the percentage of area occupied, and indicate treatment control strategies to be adopted in the field. This study was conducted by using a yellow Bourbon cultivar (IAC J10) with 1 year of implementation on a commercial coffee plantation located at Minas Gerais, Brazil. The aerial images were obtained by a remotely piloted aircraft (RPA) with an embedded multispectral sensor. Image processing was performed using PIX4D, and data analysis was performed using R and QGIS. The random forest (RF) and support vector machine (SVM) algorithms were used for the classification of the regions of interest: coffee, weed, brachiaria, and exposed soil. The differentiation between the study classes was possible due to the spectral differences between the targets, with better classification performance using the RF algorithm. The savings gained by only treating areas with the presence of weeds compared with treating the total study area are approximately 92.68%. [ABSTRACT FROM AUTHOR]

Accurate recognition of Agaricus bisporus is a prerequisite for precise automatic harvesting in a factory environment. Aimed at segmenting mushrooms adhering together from the complex background, this paper proposes a watershed-based segmentation recognition algorithm for A. bisporus. First, the foreground of A. bisporus is extracted via Otsu threshold segmentation and morphological operations. Then, a preliminary segmentation algorithm and a novel iterative marker generation method are proposed to prepare watershed markers. On this basis, a marker-controlled watershed algorithm is adopted to segment and recognize A. bisporus individuals. All the algorithms are implemented based on OpenCV (Open Source Computer Vision) libraries. Tests on images of A. bisporus collected at the cultivation bed show that the average correct recognition rate of the proposed algorithm is 95.7%, the average diameter measurement error is 1.15%, and the average coordinate deviation rate is 1.43%. The average processing time is 705.7 ms per single image, satisfying the real-time constraints based on 1 image/s. The proposed algorithm performed better than the current Circle Hough Transform (OpenCV's implementation). It is convenient and easy to operate, providing a sound basis for subsequent research on mechanized harvesting equipment for A. bisporus. [ABSTRACT FROM AUTHOR]

Corn is one of the main food crops in China, and its area ranks in the top three in the world. However, the corn leaf disease has seriously affected the yield and quality of corn. To quickly and accurately identify corn leaf diseases, taking timely and effective treatment to reduce the loss of corn yield. We proposed identifying corn leaf diseases using the Mobilenetv3 (CD-Mobilenetv3) model. Based on the Mobilenetv3 model, we replaced the model's cross-entropy loss function with a bias loss function to improve accuracy. Replaced the model's squeeze and excitation (SE) module with the efficient channel attention (ECA) module to reduce parameters. Introduced the cross-layer connections between Mobile modules to utilize features synthetically. Then we Introduced the dilated convolutions in the model to increase the receptive field. We integrated a hybrid open-source corn leaf disease dataset (CLDD). The test results on CLDD showed the accuracy reached 98.23%, the precision reached 98.26%, the recall reached 98.26%, and the F1 score reached 98.26%. The test results are improved compared to the classic deep learning (DL) models ResNet50, ResNet101, ShuffleNet_x2, VGG16, SqueezeNet, InceptionNetv3, etc. The loss value was 0.0285, and the parameters were lower than most contrasting models. The experimental results verified the validity of the CD-Mobilenetv3 model in the identification of corn leaf diseases. It provides adequate technical support for the timely control of corn leaf diseases. [ABSTRACT FROM AUTHOR]

The timely and accurate identification of stripe rust and leaf rust is essential in effective disease control and the safe production of wheat worldwide. To investigate methods for identifying the two diseases on different wheat varieties based on image processing technology, single-leaf images of the diseases on different wheat varieties, acquired under field and laboratory environmental conditions, were processed. After image scaling, median filtering, morphological reconstruction, and lesion segmentation on the images, 140 color, texture, and shape features were extracted from the lesion images; then, feature selections were conducted using methods including ReliefF, 1R, correlation-based feature selection, and principal components analysis combined with support vector machine (SVM), back propagation neural network (BPNN), and random forest (RF), respectively. For the individual-variety disease identification SVM, BPNN, and RF models built with the optimal feature combinations, the identification accuracies of the training sets and the testing sets on the same individual varieties acquired under the same image acquisition conditions as the training sets used for modeling were 87.18–100.00%, but most of the identification accuracies of the testing sets for other individual varieties were low. For the multi-variety disease identification SVM, BPNN, and RF models built with the merged optimal feature combinations based on the multi-variety disease images acquired under field and laboratory environmental conditions, identification accuracies in the range of 82.05–100.00% were achieved on the training set, the corresponding multi-variety disease image testing set, and all the individual-variety disease image testing sets. The results indicated that the identification of images of stripe rust and leaf rust could be greatly affected by wheat varieties, but satisfactory identification performances could be achieved by building multi-variety disease identification models based on disease images from multiple varieties under different environments. This study provides an effective method for the accurate identification of stripe rust and leaf rust and could be a useful reference for the automatic identification of other plant diseases. [ABSTRACT FROM AUTHOR]

Machine learning and image processing have been combined to identify and detect defects in mature citrus fruit at night, which has great research and development significance. First, a multi-light vision system was used to collect citrus UV images, and from these, 1500 samples were obtained, 80% of which were training and 20% were experimental sets. For a support vector machine (SVM) model with "2*Cb-Cr", "4*a-b-l", and "H" as the training features, the accuracy of the final training model in the experimental set is 99.67%. Then, the SVM model was used to identify mature citrus regions, detect defects, and output the defective citrus regions label. The average running time of the detection algorithm was 0.84097 s, the accuracy of citrus region detection was 95.32%, the accuracy of citrus defect detection was 96.32%, the precision was 95.24%, and the recall rate was 87.91%. The results show that the algorithm had suitable accuracy and real-time performance in recognition and defect detection in citrus in a natural environment at night. [ABSTRACT FROM AUTHOR]

Rice lodging is a crucial problem in rice production. Lodging during growing and harvesting periods can decrease rice yields. Practical lodging judgment for rice can provide effective reference information for yield prediction and harvesting. This article proposes a binocular camera-based lodging judgment method for rice in real-time. As a first step, the binocular camera and Inertial Measurement Unit (IMU) were calibrated. Secondly, Census and Grayscale Level cost features are constructed for stereo matching of left and right images. The Cross-Matching Cost Aggregation method is improved to compute the aggregation space in the LAB color space. Then, the Winner-Takes-All algorithm is applied to determine the optimal disparity for each pixel. A disparity map is constructed, and Multi-Step Disparity Refinement is applied to the disparity map to generate the final one. Finally, coordinate transformation obtains 3D world coordinates corresponding to pixels. IMU calculates the real-time pose of the binocular camera. A pose transformation is applied to the 3D world coordinates of the rice to obtain its 3D world coordinates in the horizontal state of the camera (pitch and roll angles are equal to 0). Based on the distance between the rice and the camera level, thresholding was used to determine whether the region to be detected belonged to lodging rice. The disparity map effect of the proposed matching algorithm was tested on the Middlebury Benchmark v3 dataset. The results show that the proposed algorithm is superior to the widely used Semi-Global Block Matching (SGBM) stereo-matching algorithm. Field images of rice were analyzed for lodging judgments. After the threshold judgment, the lodging region results were accurate and could be used to judge rice lodging. By combining the algorithms with binocular cameras, the research results can provide practical technical support for yield estimation and intelligent control of rice harvesters.

Deep-learning-based methods for plant disease recognition pose challenges due to their high number of network parameters, extensive computational requirements, and overall complexity. To address this issue, we propose an improved residual-network-based multi-plant disease recognition method that combines the characteristics of plant diseases. Our approach introduces a lightweight technique called maximum grouping convolution to the ResNet18 model. We made three enhancements to adapt this method to the characteristics of plant diseases and ultimately reduced the convolution kernel requirements, resulting in the final model, Model_Lite. The experimental dataset comprises 20 types of plant diseases, including 13 selected from the publicly available Plant Village dataset and seven self-constructed images of apple leaves with complex backgrounds containing disease symptoms. The experimental results demonstrated that our improved network model, Model_Lite, contains only about 1/344th of the parameters and requires 1/35th of the computational effort compared to the original ResNet18 model, with a marginal decrease in the average accuracy of only 0.34%. Comparing Model_Lite with MobileNet, ShuffleNet, SqueezeNet, and GhostNet, our proposed Model_Lite model achieved a superior average recognition accuracy while maintaining a much smaller number of parameters and computational requirements than the above models. Thus, the Model_Lite model holds significant potential for widespread application in plant disease recognition and can serve as a valuable reference for future research on lightweight network model design.

Agriculture will face significant challenges in the 21st century to feed a record number of people and animals and generate resources for industry (for example, wood, cellulose, and energy); thus, it is essential increasing yield and reducing pollution, water consumption, and energy consumption. Oliveira et al. [[7]] analysed UAV-collected RGB images to monitor dry matter yield (DMY) and nitrogen concentration in grasslands with four deep regression methods. Näsi et al. [[4]] used 27 multispectral and RGB images acquired with UAVs to assess their association with soil quality indicators, concluding that soil indicators explain the variability in UAV images in the majority of cases. [Extracted from the article]

Medicinal plants have always been studied and considered due to their high importance for preserving human health. However, identifying medicinal plants is very time-consuming, tedious and requires an experienced specialist. Hence, a vision-based system can support researchers and ordinary people in recognising herb plants quickly and accurately. Thus, this study proposes an intelligent vision-based system to identify herb plants by developing an automatic Convolutional Neural Network (CNN). The proposed Deep Learning (DL) model consists of a CNN block for feature extraction and a classifier block for classifying the extracted features. The classifier block includes a Global Average Pooling (GAP) layer, a dense layer, a dropout layer, and a softmax layer. The solution has been tested on 3 levels of definitions (64 × 64, 128 × 128 and 256 × 256 pixel) of images for leaf recognition of five different medicinal plants. As a result, the vision-based system achieved more than 99.3% accuracy for all the image definitions. Hence, the proposed method effectively identifies medicinal plants in real-time and is capable of replacing traditional methods. [ABSTRACT FROM AUTHOR]

Timely monitoring of fruit weight is a paramount concern for the improvement of productivity and quality in strawberry cultivation. Therefore, the present study was conducted to introduce a simple non-destructive technique with machine learning models in measuring fruit weight of strawberries. Nine hundred samples from three strawberry cultivars, i.e., Seolhyang, Maehyang, and Santa (300 samples in each cultivar), in six different ripening stages were randomly collected for determining length, diameter, and weight of each fruit. Pixel numbers of each captured fruit's image were calculated using image processing techniques. A simple linear-based regression (LR) and a nonlinear regression, i.e., support vector regression (SVR) models were developed by using pixel numbers as input parameter in modeling fruit weight. Findings of the study showed that the LR model performed slightly better than the SVR model in estimating fruit weight. The LR model could explain the relationship between the pixel numbers and fruit weight with a maximum of 96.3% and 89.6% in the training and the testing stages, respectively. This new method is promising non-destructive, time-saving, and cost-effective for regularly monitoring fruit weight. Hereafter, more strawberry samples from various cultivars might need to be examined for the improvement of model performance in estimating fruit weight. [ABSTRACT FROM AUTHOR]

Harvesting is an important procedure for hydroponic lettuces in plant factories. At present, hydroponic lettuces are mainly harvested manually, and the key difficulty in mechanical harvesting is reducing the occurrence of leaf injury. Measuring the size of hydroponic lettuces using the image processing method and intelligently adjusting the operating parameters of the harvesting device are the foundation of high-quality harvesting for lettuces. The overlapped leaves of adjacent hydroponic lettuces cause difficulties in measuring lettuce size, especially the leaves expansion size. Therefore, we proposed an image processing method for measuring lettuce height and leaves expansion size according to the upper contour feature of lettuces and an image included three lettuces. Firstly, the upper contours of the lettuces were extracted and segmented via image preprocessing. Secondly, lettuce height was measured according to the maximum ordinate of the contour. Lastly, the lettuce’s upper contour was fitted to a function to measure the leaves expansion size. The measurement results showed that the maximal relative error of the lettuce height measurements was 5.58%, and the average was 2.14%. The effect of the quadratic function in fitting the upper contour was the best compared with the cubic function and sine function. The maximal relative error of the leaves expansion size measurements was 8.59%, and the average was 4.03%. According to the results of the lettuce height and leaves expansion size measurements, the grabbing parameters of each lettuce were intelligently adjusted to verify the harvesting effect. The harvesting success rates of lettuces was above 90%, and the injured leaves areas of the left, middle, and right lettuces in each image were 192.6 mm2, 228.1 mm2, and 205.6 mm2, respectively. This paper provides a reference for the design and improvement of intelligent harvesters for hydroponic lettuces.

Tea is one of the most common beverages in the world. Automated machinery that is suitable for plucking high-quality green tea is necessary for tea plantations and the identification of tender leaves is one of the key techniques. In this paper, we proposed a method that combines semi-supervised learning and image processing to identify tender leaves. Both in two-dimensional and three-dimensional space, the three R, G, and B components of tender leaves and their backgrounds were trained and tested. The gradient-descent method and the Adam algorithm were used to optimize the objective function, respectively. The results show that the average accuracy of tender leaf identification is 92.62% and the average misjudgment rate is 18.86%. Our experiments have shown that green tea tender leaves in early spring can be identified effectively using the model based on semi-supervised learning, which has strong versatility and perfect adaptability, so as to improve the problem of deep learning requiring a large number of labeled samples. [ABSTRACT FROM AUTHOR]

Rice production has faced numerous challenges in recent years, and traditional methods are still being used to detect rice diseases. This research project developed an automated rice blast disease diagnosis technique based on deep learning, image processing, and transfer learning with pre-trained models such as Inception V3, VGG16, VGG19, and ResNet50. The public dataset consists of 2000 images; about 1200 images belong to the leaf blast class, and 800 to the healthy leaf class. The modified connection-skipping ResNet 50 had the highest accuracy of 99.75% with a loss rate of 0.33, while the other models achieved 98.16%, 98.47%, and 98.56%, respectively. Furthermore, ResNet 50 achieved a validation accuracy of 99.69%, precision of 99.50%, F1-score of 99.70, and AUC of 99.83%. In conclusion, the study demonstrated a superior performance and disease prediction using the Gradio web application.

In the U.S., peanut farmers receive premium prices for crops with high seed grades. One component of seed grade is the proportion of seed weight to that of pod hulls and other matter. Seed weight and size are also important traits for food processors. Current methods for evaluating peanut seed grade require the opening of the pod and are time-consuming and labor-intensive. In this study, a non-destructive and efficient method to determine peanut seed weights was investigated. X-ray images of a total of 513 peanut pods from three commercial cultivars, each representing three market types, were taken using a soft X-ray imaging system. The region of interest of each image, the seeds, was extracted two ways, manually and with a differential evolution segmentation algorithm. The comprehensive attenuation index (CAI) value was calculated from the segmented regions of interest. Lastly, linear regression models were established between peanut seed weights and the CAI. The results demonstrated that the X-ray imaging technology, coupled with the differential evolution segmentation algorithm, may be used to estimate seed weights efficiently from intact peanut pods.

Weeding operations represent an effective approach to increase crop yields. Reliable and precise weed detection is a prerequisite for achieving high-precision weed monitoring and control in precision agriculture. To develop an effective approach for detecting weeds within the red, green, and blue (RGB) images, two state-of-the-art object detection models, EfficientDet (coefficient 3) and YOLOv5m, were trained on more than 26,000 in situ labeled images with monocot/dicot classes recorded from more than 200 different fields in Denmark. The dataset was collected using a high velocity camera (HVCAM) equipped with a xenon ring flash that overrules the sunlight and minimize shadows, which enables the camera to record images with a horizontal velocity of over 50 km h-1. Software-wise, a novel image processing algorithm was developed and utilized to generate synthetic images for testing the model performance on some difficult occluded images with weeds that were properly generated using the proposed algorithm. Both deep-learning networks were trained on in-situ images and then evaluated on both synthetic and new unseen in-situ images to assess their performances. The obtained average precision (AP) of both EfficientDet and YOLOv5 models on 6625 synthetic images were 64.27% and 63.23%, respectively, for the monocot class and 45.96% and 37.11% for the dicot class. These results confirmed that both deep-learning networks could detect weeds with high performance. However, it is essential to verify both the model's robustness on in-situ images in which there is heavy occlusion with a complicated background. Therefore, 1149 in-field images were recorded in 5 different fields in Denmark and then utilized to evaluate both proposed model's robustness. In the next step, by running both models on 1149 in-situ images, the AP of monocot/dicot for EfficientDet and YOLOv5 models obtained 27.43%/42.91% and 30.70%/51.50%, respectively. Furthermore, this paper provides information regarding challenges of monocot/dicot weed detection by releasing 1149 in situ test images with their corresponding labels (RoboWeedMap) publicly to facilitate the research in the weed detection domain within the precision agriculture field. [ABSTRACT FROM AUTHOR]

This paper offers a prospective solution to the poor quality and less prominent features of the original terahertz spectral images of unsound wheat grains caused due to the imaging system and background noise. In this paper, a CBDNet-V terahertz spectral image enhancement model is proposed. Compared with the traditional algorithms, the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) of the obtained enhanced images using the proposed model show performance improvement. As validated by the ResNet-50 classification network, the proposed model processes images with an accuracy of 94.8%, and the recognition accuracy is improved by 3.7% and 1.9%, respectively, compared to the images with only denoising and feature extraction. The experimental results indicate that the deep learning-based terahertz spectral image technology for unsound wheat kernels has good prospects in the identification of unsound wheat kernels. [ABSTRACT FROM AUTHOR]

In this study, the effect of different photosynthetic photon flux density (PPFD) provided by LEDs (Light Emitting Diodes) and photoperiod on biomass production, morphological traits, photosynthetic performance, sensory attributes, and image texture parameters of indoor cultivated romaine lettuce was evaluated. Two cultivars of lettuce Lactuca sativa var. longifolium namely 'Casual' (Syngenta)—midi romaine lettuce with medium-compact heads—and 'Elizium' (Enza Zaden)—a mini type (Little Gem) with compact heavy heads—were used. PPFD of 160 and 240 µmol m−2 s−1 and photoperiod of 16 and 20 h were applied, and Daily Light Integral (DLI) values were 9.2, 11.5, 13.8, and 17.3 mol m−2 day−1. The experiment lasted 30 days in the Indoor Controlled Environment Agriculture facility. DLI equal to 17.3 mol m−2 per day for cv. 'Casual' and 11.5–17.3 mol m−2 per day for cv. 'Elizium' allowed to obtain a very high fresh weight, 350 and 240 g, respectively, within 30 days of cultivation in an indoor plant production facility. The application of the lowest PPFD 160 µmol m−2 s−1 and 16 h photoperiod (9.2 mol m−2 per day DLI) resulted in the lowest fresh weight, the number of leaves and head circumference. The level of nitrate, even at the lowest DLI, was below the limit imposed by European Community Regulation. The cv. 'Elizium' lettuce grown at PPFD 240 µmol m−2 s−1 and 16 h photoperiod had the highest overall sensory quality. The cv. 'Casual' lettuce grown at PPFD 160 µmol m−2 s−1 and 20 h photoperiod had the lowest sensory quality. The samples subjected to different photoperiod and PPFD were also successively distinguished in an objective and non-destructive way using image features and machine learning algorithms. The average accuracy for the leaf samples of cv. 'Casual' lettuce reached 98.75% and for cv. 'Elizium' cultivar—86.25%. The obtained relationship between DLI and yield, as well as the quality of romaine lettuce, can be used in practice to improve romaine lettuce production in an Indoor Controlled Environment. [ABSTRACT FROM AUTHOR]

The objective of this study was to evaluate the usefulness of machine learning based on image texture parameters to discriminate plum stone cultivars. The plums of cultivars 'Emper', 'Kalipso', and 'Polinka' were sampled. For each cultivar, one hundred images of plum stones were acquired using a digital camera. Processing of the plum stone images included the conversion of the images to individual color channels, image segmentation, region of interest (ROI) determination, and texture parameter extraction. Then, the discriminant analysis, including the texture selection and building discriminative models for the evaluation of the diversity of the plum stone cultivars, was carried out. The obtained results of discrimination of plum stone cultivars were very accurate and confirmed the effectiveness of image processing to evaluate the cultivar diversity. The most satisfactory results, reaching 96.67% for the average accuracy for three cultivars (97% for 'Emper', 'Kalipso', and 96% for 'Polinka'), were obtained for the models built based on combined textures selected from all the color channels using the IBk classifier. The developed procedure can be of practical importance for the correct identification of plum stone cultivars and avoiding their mixing to preserve cultivar uniformity. [ABSTRACT FROM AUTHOR]

Rice-fish cultivation, also known as Manipadi in Indonesia, is one of the many integrated farming systems where fish are grown concurrently with rice. However, this integrated system needs to be optimized by organic fertilizer. The application of organic fertilizers, such as compost and local biofertilizers, when implemented into this integrated system, can optimize the yield per land for both rice and fish. However, this combination must be evaluated systematically by multiple evaluation criteria and statistical analyses. Therefore, this study aimed to identify the combination of compost doses and/or local liquid organic fertilizer concentrations, based on multiple evaluation criteria, that supports the productivity of rice-fish integration agriculture. The experiment was carried out in the Wanuae farmer group of the Barebbo District, Bone Regency, Indonesia, between September 2018 and January 2019. The experiment employed a split plot design with a randomized complete block design (RCBD). The main plot consisted of compost (four levels), and the subplot was the local biofertilizer source (four levels). The results demonstrated that the number of fill grains was significantly affected by the compost treatment and the type of local biofiller. The effect of the compost dosing was more dominant in comparison with the local liquid organic fertilizer character and its interactions. A compost dosage of four tons ha−1 and a local liquid organic fertilizer, sourced from soaked coconut fiber with cow urine, has been recommended as the combination treatment to optimize the rice and fish yield potential. The Minapadi (rice fish) with additional high composting effectively increased the farmer’s outcome with a 2-point R/C ratio, more so than those without composting. Moreover, the compost dosage in this Minapadi study requires further exploration for a better understanding.

Corn is one of the main food crops in China, and its area ranks in the top three in the world. However, the corn leaf disease has seriously affected the yield and quality of corn. To quickly and accurately identify corn leaf diseases, taking timely and effective treatment to reduce the loss of corn yield. We proposed identifying corn leaf diseases using the Mobilenetv3 (CD-Mobilenetv3) model. Based on the Mobilenetv3 model, we replaced the model’s cross-entropy loss function with a bias loss function to improve accuracy. Replaced the model’s squeeze and excitation (SE) module with the efficient channel attention (ECA) module to reduce parameters. Introduced the cross-layer connections between Mobile modules to utilize features synthetically. Then we Introduced the dilated convolutions in the model to increase the receptive field. We integrated a hybrid open-source corn leaf disease dataset (CLDD). The test results on CLDD showed the accuracy reached 98.23%, the precision reached 98.26%, the recall reached 98.26%, and the F1 score reached 98.26%. The test results are improved compared to the classic deep learning (DL) models ResNet50, ResNet101, ShuffleNet_x2, VGG16, SqueezeNet, InceptionNetv3, etc. The loss value was 0.0285, and the parameters were lower than most contrasting models. The experimental results verified the validity of the CD-Mobilenetv3 model in the identification of corn leaf diseases. It provides adequate technical support for the timely control of corn leaf diseases.

Accurate recognition of Agaricus bisporus is a prerequisite for precise automatic harvesting in a factory environment. Aimed at segmenting mushrooms adhering together from the complex background, this paper proposes a watershed-based segmentation recognition algorithm for A. bisporus. First, the foreground of A. bisporus is extracted via Otsu threshold segmentation and morphological operations. Then, a preliminary segmentation algorithm and a novel iterative marker generation method are proposed to prepare watershed markers. On this basis, a marker-controlled watershed algorithm is adopted to segment and recognize A. bisporus individuals. All the algorithms are implemented based on OpenCV (Open Source Computer Vision) libraries. Tests on images of A. bisporus collected at the cultivation bed show that the average correct recognition rate of the proposed algorithm is 95.7%, the average diameter measurement error is 1.15%, and the average coordinate deviation rate is 1.43%. The average processing time is 705.7 ms per single image, satisfying the real-time constraints based on 1 image/s. The proposed algorithm performed better than the current Circle Hough Transform (OpenCV’s implementation). It is convenient and easy to operate, providing a sound basis for subsequent research on mechanized harvesting equipment for A. bisporus.

The timely and accurate identification of stripe rust and leaf rust is essential in effective disease control and the safe production of wheat worldwide. To investigate methods for identifying the two diseases on different wheat varieties based on image processing technology, single-leaf images of the diseases on different wheat varieties, acquired under field and laboratory environmental conditions, were processed. After image scaling, median filtering, morphological reconstruction, and lesion segmentation on the images, 140 color, texture, and shape features were extracted from the lesion images; then, feature selections were conducted using methods including ReliefF, 1R, correlation-based feature selection, and principal components analysis combined with support vector machine (SVM), back propagation neural network (BPNN), and random forest (RF), respectively. For the individual-variety disease identification SVM, BPNN, and RF models built with the optimal feature combinations, the identification accuracies of the training sets and the testing sets on the same individual varieties acquired under the same image acquisition conditions as the training sets used for modeling were 87.18–100.00%, but most of the identification accuracies of the testing sets for other individual varieties were low. For the multi-variety disease identification SVM, BPNN, and RF models built with the merged optimal feature combinations based on the multi-variety disease images acquired under field and laboratory environmental conditions, identification accuracies in the range of 82.05–100.00% were achieved on the training set, the corresponding multi-variety disease image testing set, and all the individual-variety disease image testing sets. The results indicated that the identification of images of stripe rust and leaf rust could be greatly affected by wheat varieties, but satisfactory identification performances could be achieved by building multi-variety disease identification models based on disease images from multiple varieties under different environments. This study provides an effective method for the accurate identification of stripe rust and leaf rust and could be a useful reference for the automatic identification of other plant diseases.

Machine learning and image processing have been combined to identify and detect defects in mature citrus fruit at night, which has great research and development significance. First, a multi-light vision system was used to collect citrus UV images, and from these, 1500 samples were obtained, 80% of which were training and 20% were experimental sets. For a support vector machine (SVM) model with “2*Cb-Cr”, “4*a-b-l”, and “H” as the training features, the accuracy of the final training model in the experimental set is 99.67%. Then, the SVM model was used to identify mature citrus regions, detect defects, and output the defective citrus regions label. The average running time of the detection algorithm was 0.84097 s, the accuracy of citrus region detection was 95.32%, the accuracy of citrus defect detection was 96.32%, the precision was 95.24%, and the recall rate was 87.91%. The results show that the algorithm had suitable accuracy and real-time performance in recognition and defect detection in citrus in a natural environment at night.

Medicinal plants have always been studied and considered due to their high importance for preserving human health. However, identifying medicinal plants is very time-consuming, tedious and requires an experienced specialist. Hence, a vision-based system can support researchers and ordinary people in recognising herb plants quickly and accurately. Thus, this study proposes an intelligent vision-based system to identify herb plants by developing an automatic Convolutional Neural Network (CNN). The proposed Deep Learning (DL) model consists of a CNN block for feature extraction and a classifier block for classifying the extracted features. The classifier block includes a Global Average Pooling (GAP) layer, a dense layer, a dropout layer, and a softmax layer. The solution has been tested on 3 levels of definitions (64 × 64, 128 × 128 and 256 × 256 pixel) of images for leaf recognition of five different medicinal plants. As a result, the vision-based system achieved more than 99.3% accuracy for all the image definitions. Hence, the proposed method effectively identifies medicinal plants in real-time and is capable of replacing traditional methods.

Tea is one of the most common beverages in the world. Automated machinery that is suitable for plucking high-quality green tea is necessary for tea plantations and the identification of tender leaves is one of the key techniques. In this paper, we proposed a method that combines semi-supervised learning and image processing to identify tender leaves. Both in two-dimensional and three-dimensional space, the three R, G, and B components of tender leaves and their backgrounds were trained and tested. The gradient-descent method and the Adam algorithm were used to optimize the objective function, respectively. The results show that the average accuracy of tender leaf identification is 92.62% and the average misjudgment rate is 18.86%. Our experiments have shown that green tea tender leaves in early spring can be identified effectively using the model based on semi-supervised learning, which has strong versatility and perfect adaptability, so as to improve the problem of deep learning requiring a large number of labeled samples.

Mobile applications that can be used for the training and classification of plant diseases are described in this paper. Professional agronomists can select the species and their diseases that are supported by the developed tool and follow an automatic training procedure using a small number of indicative photographs. The employed classification method is based on features that represent distinct aspects of the sick plant such as, for example, the color level distribution in the regions of interest. These features are extracted from photographs that display a plant part such as a leaf or a fruit. Multiple reference ranges are determined for each feature during training. When a new photograph is analyzed, its feature values are compared with the reference ranges, and different grades are assigned depending on whether a feature value falls within a range or not. The new photograph is classified as the disease with the highest grade. Ten tomato diseases are used as a case study, and the applications are trained with 40–100 segmented and normalized photographs for each disease. An accuracy between 93.4% and 96.1% is experimentally measured in this case. An additional dataset of pear disease photographs that are not segmented or normalized is also tested with an average accuracy of 95%.

In this study, the effect of different photosynthetic photon flux density (PPFD) provided by LEDs (Light Emitting Diodes) and photoperiod on biomass production, morphological traits, photosynthetic performance, sensory attributes, and image texture parameters of indoor cultivated romaine lettuce was evaluated. Two cultivars of lettuce Lactuca sativa var. longifolium namely ‘Casual’ (Syngenta)—midi romaine lettuce with medium-compact heads—and ‘Elizium’ (Enza Zaden)—a mini type (Little Gem) with compact heavy heads—were used. PPFD of 160 and 240 µmol m−2 s−1 and photoperiod of 16 and 20 h were applied, and Daily Light Integral (DLI) values were 9.2, 11.5, 13.8, and 17.3 mol m−2 day−1. The experiment lasted 30 days in the Indoor Controlled Environment Agriculture facility. DLI equal to 17.3 mol m−2 per day for cv. ‘Casual’ and 11.5–17.3 mol m−2 per day for cv. ‘Elizium’ allowed to obtain a very high fresh weight, 350 and 240 g, respectively, within 30 days of cultivation in an indoor plant production facility. The application of the lowest PPFD 160 µmol m−2 s−1 and 16 h photoperiod (9.2 mol m−2 per day DLI) resulted in the lowest fresh weight, the number of leaves and head circumference. The level of nitrate, even at the lowest DLI, was below the limit imposed by European Community Regulation. The cv. ‘Elizium’ lettuce grown at PPFD 240 µmol m−2 s−1 and 16 h photoperiod had the highest overall sensory quality. The cv. ‘Casual’ lettuce grown at PPFD 160 µmol m−2 s−1 and 20 h photoperiod had the lowest sensory quality. The samples subjected to different photoperiod and PPFD were also successively distinguished in an objective and non-destructive way using image features and machine learning algorithms. The average accuracy for the leaf samples of cv. ‘Casual’ lettuce reached 98.75% and for cv. ‘Elizium’ cultivar—86.25%. The obtained relationship between DLI and yield, as well as the quality of romaine lettuce, can be used in practice to improve romaine lettuce production in an Indoor Controlled Environment.

This paper offers a prospective solution to the poor quality and less prominent features of the original terahertz spectral images of unsound wheat grains caused due to the imaging system and background noise. In this paper, a CBDNet-V terahertz spectral image enhancement model is proposed. Compared with the traditional algorithms, the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) of the obtained enhanced images using the proposed model show performance improvement. As validated by the ResNet-50 classification network, the proposed model processes images with an accuracy of 94.8%, and the recognition accuracy is improved by 3.7% and 1.9%, respectively, compared to the images with only denoising and feature extraction. The experimental results indicate that the deep learning-based terahertz spectral image technology for unsound wheat kernels has good prospects in the identification of unsound wheat kernels.

The objective of this study was to evaluate the usefulness of machine learning based on image texture parameters to discriminate plum stone cultivars. The plums of cultivars ‘Emper’, ‘Kalipso’, and ‘Polinka’ were sampled. For each cultivar, one hundred images of plum stones were acquired using a digital camera. Processing of the plum stone images included the conversion of the images to individual color channels, image segmentation, region of interest (ROI) determination, and texture parameter extraction. Then, the discriminant analysis, including the texture selection and building discriminative models for the evaluation of the diversity of the plum stone cultivars, was carried out. The obtained results of discrimination of plum stone cultivars were very accurate and confirmed the effectiveness of image processing to evaluate the cultivar diversity. The most satisfactory results, reaching 96.67% for the average accuracy for three cultivars (97% for ‘Emper’, ‘Kalipso’, and 96% for ‘Polinka’), were obtained for the models built based on combined textures selected from all the color channels using the IBk classifier. The developed procedure can be of practical importance for the correct identification of plum stone cultivars and avoiding their mixing to preserve cultivar uniformity.

Tetranychus urticae Koch is an important citrus pest that produces chlorotic spots on the leaves and scars on the fruit of affected trees. It is detected by visual inspection of the leaves. This work studies the potential of colour and hyperspectral imaging (400–1000 nm) under laboratory conditions as a fast and automatic method to detect the damage caused by this pest. The ability of a traditional vision system to differentiate this pest from others, such as Phyllocnistis citrella, and other leaf problems such as those caused by nutritional deficiencies, has been studied and compared with a more advanced hyperspectral system. To analyse the colour images, discriminant analysis has been used to classify the pixels as belonging to either a damaged or healthy leaves. In contrast, the hyperspectral images have been analysed using PLS DA. The rate of detection of the damage caused by T. urticae with colour images reached 92.5%, while leaves that did not present any damage were all correctly identified. Other problems such as damage by P. citrella were also correctly discriminated from T. urticae. Moreover, hyperspectral imaging allowed damage caused by T. urticae to be discriminated from healthy leaves and to distinguish between recent and mature leaves, which indicates whether it is a recent or an older infestation. Furthermore, good results were achieved in the discrimination between damage caused by T. urticae, P. citrella, and nutritional deficiencies.

Fungi such as Aspergillus flavus and Aspergillus parasiticus are molds infecting food and animal feed, are responsible for aflatoxin contamination, and cause a significant problem for human and animal health. The detection of aflatoxin and aflatoxigenic fungi on raw material is a major concern to protect health, secure food and feed, and preserve their value. The effectiveness of image processing, combined with computational techniques, has been investigated to detect and segregate peanut (Arachis hypogaea L.) seeds infected with an aflatoxin producing fungus. After inoculation with Aspergillus flavus, images of peanuts seeds were taken using various lighting sources (LED, UV, and fluorescent lights) on two backgrounds (black and white) at 0, 48, and 72 h after inoculation. Images were post-processed with three different machine learning tools: the artificial neural network (ANN), the support vector machine (SVM), and the adaptive neuro-fuzzy inference system (ANFIS) to detect the Aspergillus flavus growth on peanuts. The results of the study show that the combination of LED light and a white background with ANN had 99.7% accuracy in detecting fungal growth on peanuts 72 h from infection with Aspergillus. Additionally, UV lights and a black background with ANFIS achieve 99.9% accuracy in detecting fungal growth on peanuts 48 h after their infection with Aspergillus.

The European Commission introduces the Control by Monitoring through new technologies to manage Common Agricultural Policy funds through the Regulation 2018/746. The advances in remote sensing have been considered one of these new technologies, mainly since the European Space Agency designed the Copernicus Programme. The Sentinel-1 (radar range) and Sentinel-2 (optical range) satellites have been designed for monitoring agricultural problems based on the characteristics they provide. The data provided by the Sentinel 2 missions, together with the emergence of different scientific disciplines in artificial intelligence —especially machine learning— offer the perfect basis for identifying and classifying any crop and its phenological state. Our research is based on developing and evaluating a pixel-based supervised classification scheme to produce accurate rice crop mapping in a smallholder agricultural zone in Calasparra, Murcia, Spain. Several models are considered to obtain the most suitable model for each element of the time series used; pixel-based classification is performed and finished with a statistical treatment. The highly accurate results obtained, especially across the most significant vegetative development dates, indicate the benefits of using Sentinel-2 data combined with Machine Learning techniques to identify rice crops. It should be noted that it was possible to locate rice crop areas with an overall accuracy of 94% and standard deviation of 1%, which could be increased to 96% (±1%) if we focus on the months of the crop’s highest development state. Thanks to the proposed methodology, the on-site inspections carried out, 5% of the files, have been replaced by remote sensing evaluations of 100% of the analyzed season files. Besides, by adjusting the model input data, it is possible to detect unproductive or abandoned plots.

Field weeds identification is challenging for precision spraying, i.e., the automation identification of the weeds from the crops. For rapidly obtaining weed distribution in field, this study developed a weed density detection method based on absolute feature corner point (AFCP) algorithm for the first time. For optimizing the AFCP algorithm, image preprocessing was firstly performed through a sub-module processing capable of segmenting and optimizing the field images. The AFCP algorithm improved Harris corner to extract corners of single crop and weed and then sub-absolute corner classifier as well as absolute corner classifier were proposed for absolute corners detection of crop rows. Then, the AFCP algorithm merged absolute corners to identify crop and weed position information. Meanwhile, the weed distribution was obtained based on two weed density parameters (weed pressure and cluster rate). At last, the AFCP algorithm was validated based on the images that were obtained using one typical digital camera mounted on the tractor in field. The results showed that the proposed weed detection method manifested well given its ability to process an image of 2748 × 576 pixels using 782 ms as well as its accuracy in identifying weeds reaching 90.3%. Such results indicated that the weed detection method based on AFCP algorithm met the requirements of practical weed management in field, including the real-time images computation processing and accuracy, which provided the theoretical base for the precision spraying operations.

Due to the importance of identifying crop cultivars, the advancement of accurate assessment of cultivars is considered essential. The existing methods for identifying rice cultivars are mainly time-consuming, costly, and destructive. Therefore, the development of novel methods is highly beneficial. The aim of the present research is to classify common rice cultivars in Iran based on color, morphologic, and texture properties using artificial intelligence (AI) methods. In doing so, digital images of 13 rice cultivars in Iran in three forms of paddy, brown, and white are analyzed through pre-processing and segmentation of using MATLAB. Ninety-two specificities, including 60 color, 14 morphologic, and 18 texture properties, were identified for each rice cultivar. In the next step, the normal distribution of data was evaluated, and the possibility of observing a significant difference between all specificities of cultivars was studied using variance analysis. In addition, the least significant difference (LSD) test was performed to obtain a more accurate comparison between cultivars. To reduce data dimensions and focus on the most effective components, principal component analysis (PCA) was employed. Accordingly, the accuracy of rice cultivar separations was calculated for paddy, brown rice, and white rice using discriminant analysis (DA), which was 89.2%, 87.7%, and 83.1%, respectively. To identify and classify the desired cultivars, a multilayered perceptron neural network was implemented based on the most effective components. The results showed 100% accuracy of the network in identifying and classifying all mentioned rice cultivars. Hence, it is concluded that the integrated method of image processing and pattern recognition methods, such as statistical classification and artificial neural networks, can be used for identifying and classification of rice cultivars.

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. [ABSTRACT FROM AUTHOR]

The number of rice grains on a panicle is an important index for variety screening during high-quality rice [Oryza Sativa L.] breeding. For an in-vivo image-based measurement, the occlusion and overlapping among grains are the major challenges in non-destructive precise phenotyping of the on-panicle grains. In order to tackle these challenges, this paper describes a correction-model-referred on-panicle grain counting method based on the area of the rice panicle and its edge contour wavelet analysis. First, we assume that a deterministic correlation exists between the number of grains of the panicle and the traits of its edge contour morphology, which reflects the extent to which the grains are occluded. Second, a method for coarsely estimating grain number per panicle is proposed based on the projective area of the panicle in the image and the average area of a rice grain. Finally, a correction model which is built with the average wavelet frequency of the edge contour of the panicle is employed to correct the estimated value of the grain number. Two randomly selected cases are investigated in detail, showing that computation accuracy with a correction model is increased by 26% and 23% respectively when compared to that of the naive area-based computation. In conclusion, we reveal and validate the relationship between the number of grains of the panicle and the fluctuation frequency of its edge contours. Further, experiments show that errors caused by overlapping and occlusion scenarios can be alleviated with the estimation and correction hybrid models, achieving an average accuracy of 94% compared to the results of manual counting. [ABSTRACT FROM AUTHOR]

Image-based evaluation of phenotypic traits has been applied for plant architecture, seed, canopy growth/vigor, and root characterization. However, such applications using computer vision have not been exploited for the purpose of assessing the coleoptile length and herbicide injury in seeds. In this study, high-throughput phenotyping using digital image analysis was applied to evaluate seed/seedling traits. Images of seeds or seedlings were acquired using a commercial digital camera and analyzed using custom-developed image processing algorithms. Results from two case studies demonstrated that it was possible to use image-based high-throughput phenotyping to assess seeds/seedlings. In the seedling evaluation study, using a color-based detection method, image-based and manual coleoptile length were positively and significantly correlated (p < 0.0001) with reasonable accuracy (r = 0.69-0.91). As well, while using a width-and-color-based detection method, the correlation coefficient was also significant (p < 0.0001, r = 0.89). The improvement of the germination protocol designed for imaging will increase the throughput and accuracy of coleoptile detection using image processing methods. In the herbicide study, using image-based features, differences between injured and uninjured seedlings can be detected. In the presence of the treatment differences, such a technique can be applied for non-biased symptom rating. [ABSTRACT FROM AUTHOR]

The number of rice grains on a panicle is an important index for variety screening during high-quality rice [Oryza Sativa L.] breeding. For an in-vivo image-based measurement, the occlusion and overlapping among grains are the major challenges in non-destructive precise phenotyping of the on-panicle grains. In order to tackle these challenges, this paper describes a correction-model-referred on-panicle grain counting method based on the area of the rice panicle and its edge contour wavelet analysis. First, we assume that a deterministic correlation exists between the number of grains of the panicle and the traits of its edge contour morphology, which reflects the extent to which the grains are occluded. Second, a method for coarsely estimating grain number per panicle is proposed based on the projective area of the panicle in the image and the average area of a rice grain. Finally, a correction model which is built with the average wavelet frequency of the edge contour of the panicle is employed to correct the estimated value of the grain number. Two randomly selected cases are investigated in detail, showing that computation accuracy with a correction model is increased by 26% and 23% respectively when compared to that of the naive area-based computation. In conclusion, we reveal and validate the relationship between the number of grains of the panicle and the fluctuation frequency of its edge contours. Further, experiments show that errors caused by overlapping and occlusion scenarios can be alleviated with the estimation and correction hybrid models, achieving an average accuracy of 94% compared to the results of manual counting.

Mobile applications that can be used for the training and classification of plant diseases are described in this paper. Professional agronomists can select the species and their diseases that are supported by the developed tool and follow an automatic training procedure using a small number of indicative photographs. The employed classification method is based on features that represent distinct aspects of the sick plant such as, for example, the color level distribution in the regions of interest. These features are extracted from photographs that display a plant part such as a leaf or a fruit. Multiple reference ranges are determined for each feature during training. When a new photograph is analyzed, its feature values are compared with the reference ranges, and different grades are assigned depending on whether a feature value falls within a range or not. The new photograph is classified as the disease with the highest grade. Ten tomato diseases are used as a case study, and the applications are trained with 40–100 segmented and normalized photographs for each disease. An accuracy between 93.4% and 96.1% is experimentally measured in this case. An additional dataset of pear disease photographs that are not segmented or normalized is also tested with an average accuracy of 95%. [ABSTRACT FROM AUTHOR]