Figure - available from: International Journal of Intelligent Robotics and Applications
This content is subject to copyright. Terms and conditions apply.
some examples of the bean leaves, which are classified correctly using the proposed system after accurately detecting the bean leaves in the input image and misclassified them without applying the image segmentation step
Source publication
The bean leaves can be affected by several diseases, such as angular leaf spots and bean rust, which can cause big damage to bean crops and decrease their productivity. Thus, treating these diseases in their early stages can improve the quality and quantity of the product. Recently, several robotic frameworks based on image processing and artificia...
Similar publications
ResNet50 and VGG-16 models are introduced in this paper with different strategies, with and without preprocessing and with and without Support Vector Machine (SVM). Moreover, both transfer learning and data augmentation are used to solve the problem of lack of tagged data. The fully connected (FC) layer is replaced by the SVM classifier leading to...
Citations
... The model results are better in terms of recall, precision, and accuracy. Abed et al. (2021) presented a novel deep learning model for bean leaf disease detection. This model contains two phases: detection and diagnosing. ...
Tomato is one of the most popular and most important food crops consumed globally. The quality and quantity of yield by tomato plants are affected by the impact made by various kinds of diseases. Therefore, it is essential to identify these diseases early so that it is possible to reduce the occurrences and effect of the diseases on tomato plants to improve the overall crop yield and to support the farmers. In the past, many research works have been carried out by applying the machine learning techniques to segment and classify the tomato leaf images. However, the existing machine learning-based classifiers are not able to detect the new types of diseases more accurately. On the other hand, deep learning-based classifiers with the support of swarm intelligence-based optimization techniques are able to enhance the classification accuracy, leading to the more effective and accurate detection of leaf diseases. This research paper proposes a new method for the accurate classification of tomato leaf diseases by harnessing the power of an ensemble model in a sample dataset of tomato plants, containing images pertaining to nine different types of leaf diseases. This research introduces an ensemble model with an exponential moving average function with temporal constraints and an enhanced weighted gradient optimizer that is integrated into fine-tuned Visual Geometry Group-16 (VGG-16) and Neural Architecture Search Network (NASNet) mobile training methods for providing improved learning and classification accuracy. The dataset used for the research consists of 10,000 tomato leaf images categorized into nine classes for training and validating the model and an additional 1,000 images reserved for testing the model. The results have been analyzed thoroughly and benchmarked with existing performance metrics, thus proving that the proposed approach gives better performance in terms of accuracy, loss, precision, recall, receiver operating characteristic curve, and F1-score with values of 98.7%, 4%, 97.9%, 98.6%, 99.97%, and 98.7%, respectively.
... The main advantage of this approach was that it required fewer training parameters, which ultimately reduced the analysis time. Abed et al. (2021) proposed a framework that detects bean leaves and diagnoses diseases within the detected leaves using a pre-trained ResNet34 encoder. Five different deep-learning models were evaluated to identify the healthiness of bean leaves. ...
Background: Legumes, such as lentils, field peas, Faba beans and chickpeas, are high in vitamins, fiber, important minerals and protein and can help avoid obesity and cardiovascular illnesses. They also contribute to ecosystem services, such as nitrogen fixation and resilience to environmental stresses. Despite a 60% increase in global pulse production from 2000 to 2021, a demand-supply gap, especially in South Asia, raises concerns about nutritional access. Since illnesses are currently an issue to the food security of faba beans, machine learning is required for efficient disease identification. Methods: This research employs Convolutional Neural Networks (CNNs) for robust Faba bean leaf disease identification. The CNN model is trained with diverse images representing specific diseases. The study focuses on diseases like Chocolate Spot, Faba Bean Gall, Rust and Healthy leaves. Image processing involves resizing, grayscale conversion and labeling. The CNN architecture includes eight convolutional layers, four max-pooling layers and three dropout layers. The model is trained using 80% of the dataset, validated using 20% and tested for accuracy. Result: The CNN model achieves an accuracy of 99.37% during training and 89.69% during validation after 75 epochs. Confusion matrix and classification report illustrate the model’s performance. It shows high precision, recall and F1 scores for each class, indicating balanced performance. Chocolate Spot and Rust exhibit the highest precision and F1 scores. The overall accuracy is 91%, comparable to other studies on Faba bean disease detection. The study presents a CNN-based disease identification system for Faba beans, demonstrating high accuracy and balanced performance across different diseases. The model’s effectiveness is comparable to other advanced techniques. The research highlights the potential of machine learning in optimizing disease management for Faba beans. Future work could explore a broader range of diseases and incorporate hybrid machine learning algorithms for further improvement.
... By examining the movement patterns of the intended subject, the movement characteristics are extracted, and ultimately, the movement prediction is achieved. The human can achieve this prediction through observation, which showcases the heightened cognitive abilities of humans [5]. From the perception of interactions between humans and robots or robots with each other, this skill becomes especially vital for monitoring the movement of the entity. ...
In contrast to the machine, people have strong perception to determine the multiple objects easily in various environments under certain conditions. It is evident that the objects may exist in different orientations, scales and/or shapes, however it does not affect our ability to correct object recognition accuracy. The computer vision based object recognition is one of the most tedious tasks. So, objective is to design and development of the robust object recognition system to recognize the multiple objects effectively since different variations in the natural images are existed. In this paper, authors have presented comparative analysis and studies of some state of art object-recognition models for robot vision based problems, where the main goal is to recognize position, orientations and the identity of objects/parts, where parts have been taken from the industry. In the dynamic environment problem, the parts are recognized in a complex scenario. This paper presented based on the object representations using the recognition algorithms. Three steps are discussed and examined in details which are common to each and every category, namely, feature extraction, modeling, and matching. Test results confirmed that proposed model-based recognition in robot vision is fast and provides 93.00% accuracy. The proposed algorithm for object-recognition model has been compared with existing industrial part-recognition models and has, provided insights for progress toward future robot vision systems.
... Abed et al. [9] proposed a robot vision for automating bean leaf disease detection. The researchers tackled the problem as a binary classification task and multiclass classification tasks then used Deep Learning models to classify bean leaf images. ...
... The following table shows the comparison between the optimized model and existing models. In terms of the number of parameters, the model has 57.4% less parameters than that of the model proposed by [7] and 59.7% less parameters compared to that of [9]. In Deep Learning, a high number of parameters equates to high processing and inference requirements. ...
Crops play a vital role in human nutrition and overall well-being. Beans are an economically significant type of crops that not only provide a rich source of protein but also offers substantial health benefits. However, beans are susceptible to bacterial and fungal infections. If left uncontrolled, these diseases could result in severe consequences. Diagnosis of the affected leaves can be done by plant pathologists, which is not readily available in local and remote areas. Using deep learning algorithms, an accurate classification of bean leaf diseases can offset this problem from an early stage. This research introduces a framework for optimizing MobileNetV3 using Particle Swarm Optimization that can accurately identify healthy or diseased bean leaves from images captured in real-world conditions. With having only 2.9M parameters, the best model achieved a high degree of accuracy at 98.44% on unseen data, outperforming the models proposed by other researchers on the same classification task. Results suggest that the model can be adopted in the field to increase the efficiency in the early identification of bean leaf diseases. Lastly, the same methodology can also be applied in solving plant leaf diseases from other economically significant crops.
... The graph from Fig. 23 shows how sensitive the three different algorithms are. The support vector machine algorithm's high sensitivity rating 28,32 in this instance indicates that the actual positive values predicted using that approach are very accurate. By incorporating a sizable amount of data from numerous plants in various places, the model will be constructed. ...
Detecting diseases is a vital and crucial step in maintaining healthy, high-yielding plants. The challenge of manually identifying infections is arduous as well. The proposed work is to diagnose plant leaf diseases and discuss their origins and remedies. Image processing is used to discover the infected leaf and provide remedial measures through a mobile robot application. The use of machine learning techniques allows for the detection of leaf diseases using the support vector machine model, the K nearest neighbor model, and the Naïve Bayes classification to categorize the sample leaves. In this paper, the Momordica charantia leaf and the common four diseases dataset are developed, and a classification model is developed to identify and categorize leaf curl, downy mildew, powdery mildew, and angular leaf spot. Based on the disease classification, appropriate chemical pesticides are sprayed by controlling the servo actuated valve in the proposed agriculture robot, which is controlled and validated. The result reveals that the proposed approach has an average accuracy of 82% in identifying the disease type that remains more prevalent in Momordica charantia leaves than other compared classification algorithms.
... Similar tests were conducted on the "MNIST" dataset as a benchmark, achieving a validation accuracy of 11.7%; since the "MNIST" dataset only has 10 classes, 11.7% is an appropriate value for random guesses, showing no bias. Similarly, many papers utilising the "NaCRRI" Ugandan public dataset have consistently achieved a validation accuracy of above 98%, which is considered suspicious as it seems similar to the "Plant village" bias [Devi et al., 2023;Elfatimi et al., 2022;Abed et al., 2021;. The "NaCRRI" Ugandan public dataset tends to have variations in data collection; for example, the leaf would be plucked, and at other times, it would be on the plant. ...
Amidst growing food production demands, early plant disease detection is essential to safeguard crops; this study proposes a visual machine learning approach for plant disease detection , harnessing RGB and NIR data collected in real-world conditions through a JAI FS-1600D-10GE camera to build an RGBN dataset. A two-stage early plant disease detection model with YOLOv8 and a sequential CNN was used to train on a dataset with partial labels, which showed a 3.6% increase in mAP compared to a single-stage end-to-end segmentation model. The sequential CNN model achieved 90.62% validation accuracy utilising RGBN data. An average of 6.25% validation accuracy increase is found using RGBN in classification compared to RGB using ResNet15 and the sequential CNN models. Further research and dataset improvements are needed to meet food production demands.
... The results showed that the OMNCNN model outperformed the latest state-of-the-art techniques, achieving a maximum precision accuracy of 0.987, indicating promising outcomes. Sudad et al. [32] proposed a method based on deep learning for detecting bean leaf diseases. The framework consists of two primary stages: detecting the bean leaves in input images and diagnosing the diseases within the detected leaves. ...
Bean is a widely cultivated crop worldwide; however, it is susceptible to various diseases that can adversely affect the quality of beans, including rust and angular leaf spot diseases. These diseases can cause significant damage by wiping out hectares of crops, emphasizing the need for early detection. Deep learning algorithms have shown remarkable performance in image detection tasks, achieving high accuracy on many datasets. This study used a deep learning technique, specifically the MobileNet architecture, to detect bean leaf disease. We evaluated the effectiveness of the approach by testing the model on three different bean leaf image datasets with varying difficulty. MobileNet was chosen due to its ability to achieve high performance with a reduced number of parameters and faster execution time. Additionally, we examined the impact of the datasets on the model’s performance and presented a comparative analysis of the three datasets, and then we applied the GradCAM technique to the model’s predictions. Experimental results showed that the proposed approach achieved remarkable accuracy, with over 92% accuracy on all three datasets. The study provides a valuable contribution to the field of plant disease detection and highlights the potential of deep learning techniques in detecting bean leaf disease.
... To assess the accuracy of the timber and leaf discrimination from point clouds, six ML algorithms, RF, naive Bayes (NB), gradient boosting machine (GBM), deep learning (DL), generalized linear model (GLM), and stacked ensemble model (EN; Table 2), were used. These ML algorithms were chosen due to their ease of use, computational efficiency, and well-established performance for the binary-class and multi-class classifications involving the discrimination of leaf (class 1) and wood (class 2) [14,27,40,41]. ...
... Adjusting the activation and hidden settings in DL enhanced the model learning capacity to explore the classification patterns. The Laplace smoothing setting in NB addressed the issue of zero probability in the naive Bayes machine learning algorithm [41,51,59]. Table 3. Hyperparameters set for optimizing models for RF (random forest), DL (deep learning), GBM (gradient boosting machine), and NB (naive Bayes). ...
... Despite the contrasting F1 scores and OA results in the multi-class and binary-class classifications, the observed commission and omission error patterns displayed in Figure 5 allow us to assume that the multi-class classification is not a reliable method for matching top-performing ML-derived models with tree species. The same results, however, emphasize the significance of this approach for other classification tasks, such as tree-species categorization and other ecological metric evaluations [41,74]. ...
Terrestrial laser scanning (TLS) technology characterizes standing trees with millimetric precision. An important step to accurately quantify tree volume and above-ground biomass using TLS point clouds is the discrimination between timber and leaf components. This study evaluates the performance of machine learning (ML)-derived models aimed at discriminating timber and leaf TLS point clouds, focusing on eight Mediterranean tree species datasets. The results show the best accuracies for random forests, gradient boosting machine, stacked ensemble model, and deep learning models with an average F1 score equal to 0.92. The top-performing ML-derived models showed well-balanced average precision and recall rates, ranging from 0.86 to 0.91 and 0.92 to 0.96 for precision and recall, respectively. Our findings show that Italian maple, European beech, hazel, and small-leaf lime tree species have more accurate F1 scores, with the best average F1 score of 0.96. The factors influencing the timber–leaf discrimination include phenotypic factors, such as bark surface (i.e., roughness and smoothness), technical issues (i.e., noise points and misclassification of points), and secondary factors (i.e., bark defects, lianas, and microhabitats). The top-performing ML-derived models report a time computation ranging from 8 to 37 s for processing 2 million points. Future studies are encouraged to calibrate, configure, and validate the potential of top-performing ML-derived models on other tree species and at the plot level.
... They used Raspberry Pi 4 and Arduino microcontrollers in the hardware prototypes. Authors in [25,26] developed a robotic system for the detection of plant diseases. They used different ML algorithms such as the principal component analysis algorithm, Densenet121, ResNet34, ResNet50, and VGG-16. ...
Cotton is one of the most important agricultural products and is closely linked to the economic development of Pakistan. However, the cotton plant is susceptible to bacterial and viral diseases that can quickly spread and damage plants and ultimately affect the cotton yield. The automated and early detection of affected plants can significantly reduce the potential spread of the disease. This paper presents the implementation and performance analysis of bacterial blight and curl virus disease detection in cotton crops through deep learning techniques. The automated disease detection is performed through transfer learning of six pre-trained deep learning models, namely DenseNet121, DenseNet169, MobileNetV2, ResNet50V2, VGG16, and VGG19. A total of 1362 images of local agricultural fields and 1292 images from online resources were used to train and validate the models. Image augmentation techniques were performed to increase the dataset diversity and size. Transfer learning was implemented for different image resolutions ranging from 32×32 to 256×256 pixels. Performance metrics such as accuracy, precision, recall, F1 Score, and prediction time were evaluated for each implemented model. The results indicate higher accuracy, up to 96%, for DenseNet169 and ResNet50V2 models when trained on the 256×256 pixels image dataset. The lowest accuracy, 52%, was obtained by the MobileNetV2 model when trained on low-resolution, 32×32, images. The confusion matrix analysis indicates the true-positive prediction rates higher than 91% for fresh leaves, 87% for bacterial blight, and 76% for curl virus detection for all implemented models when trained and tested on an image dataset of 128×128 pixels or higher resolution.
... Another instance of a deep learning model was developed in order to detect bean leaf diseases automatically was made by Sudad H. Abed, Alaa S. Al-Waisy, Hussain J. Mohammed and Shumoos Al-Fahdawi, which was evaluated on 1295 images and their best performance in binary classification task was achieved using Densenet121 model with a CAR of 98.31%, Precision of 98.45% and F1 score of 98.74% [2]. ...
Beans are a crucial protein source, but disease-infected crops like angular spot leaf disease and bean rust can cause financial and physical problems. A detection system is essential to prevent crop loss and ensure farmers can take appropriate actions. A convolutional neural network algorithm called AlexNet has been used to detect if a bean crop is infected or not. In this research paper, we trained AlexNet to classify if the beans are healthy or infected from the bean leaf images dataset with one class being healthy and the other class being infected. The AlexNet model achieved 99.7% accuracy on the training dataset and 96.8% accuracy on the test set, including diseased bean leaves for verification, instruction, and evaluation.
