Enhanced Plant Leaf Disease Detection Using CLAHE-Processed Images and Custom CNN Deep Learning Architecture

Crop disease is a serious concern for safety of food, but its fast detection still remains difficult in different parts of the world because of the lack of proper infrastructure. Automatic identification of plant diseases is necessary for food security, yield loss estimation and management of disease. With the worldwide increase in digital cameras and continuous improvement in computer vision domain, the automated techniques for detection of disease are highly in demands in precision agriculture, highly productive plant phenotype, smart greenhouse and much more. Working on an open dataset which includes 15200 images of crop leaves, a Residual Network (ResNet34) was trained to perform this task of classification. The proposed ResNet34 model accomplished a 99.40% accuracy on a test set, illustrating the viability of the proposed model. Overall, the process of training ResNet models on an open image dataset provides a sound way towards crop disease detection using automated networks on an enormous global scale.

Pest infestation is a significant challenge in agriculture, causing substantial economic losses and impacting crop yields. Manual pest identification is time-consuming and error-prone, especially in large-scale farming. This study presents a hybrid deep learning approach to automate pest detection and classification using image data. It employs a pre-trained VGG16 model for robust feature extraction, followed by a custom Convolutional Neural Network (CNN) for classification. The VGG16 model leverages transfer learning to capture high-level visual patterns from pest images, while the custom CNN is trained on these features to distinguish between multiple pest classes. The proposed pipeline is optimized using data augmentation, early stopping, and adaptive learning techniques. Performance is evaluated using metrics such as accuracy, precision, recall, and F1-score. The model demonstrates high accuracy and robustness on agricultural image datasets, making it a scalable solution for smart farming systems. Index Terms: Pest Detection, Deep Learning, VGG16, Convolutional Neural Network, Transfer Learning, Image Classification, Precision Agriculture, Feature Extraction.

In the era of smart agriculture, accurate identification of plant species is critical for effective crop management, biodiversity monitoring, and the sustainable use of medicinal resources. However, existing deep learning approaches often underperform when applied to fine-grained plant classification tasks due to the lack of domain-specific, high-quality datasets and the limited representational capacity of traditional architectures. This study addresses these challenges by introducing a novel, well-curated leaf image dataset consisting of 39 classes of medicinal and aromatic plants collected from the Aromatic and Medicinal Plant Research Station in Odakkali, Kerala, India. To overcome performance bottlenecks observed with a baseline Convolutional Neural Network (CNN) that achieved only 44.94% accuracy, we progressively enhanced model performance through a series of architectural innovations. These included the use of a pre-trained VGG16 network, data augmentation techniques, and fine-tuning of deeper convolutional layers, followed by the integration of Squeeze-and-Excitation (SE) attention blocks. Ultimately, we propose a hybrid deep learning architecture that combines VGG16 with Batch Normalization, Gated Recurrent Units (GRUs), Transformer modules, and Dilated Convolutions. This final model achieved a peak validation accuracy of 95.24%, significantly outperforming several baseline models, such as custom CNN (44.94%), VGG-19 (59.49%), VGG-16 before augmentation (71.52%), Xception (85.44%), Inception v3 (87.97%), VGG-16 after data augumentation (89.24%), VGG-16 after fine-tuning (90.51%), MobileNetV2 (93.67), and VGG16 with SE block (94.94%). These results demonstrate superior capability in capturing both local textures and global morphological features. The proposed solution not only advances the state of the art in plant classification but also contributes a valuable dataset to the research community. Its real-world applicability spans field-based plant identification, biodiversity conservation, and precision agriculture, offering a scalable tool for automated plant recognition in complex ecological and agricultural environments.

In agriculture, the early and accurate identification of plant diseases is an important step in increasing crop yield. Leaf disease detection is one of the most widely used methods for identifying plant diseases. In recent years, automatic and accurate classification of plant leaf diseases has attracted increasing research attention. With the emergence of deep neural networks (DNN), the identification and classification of plant leaf diseases have achieved competitive results. This study proposes a method based on data augmentation techniques and advanced deep neural network models to improve the accuracy of the identification and classification of plant leaf diseases. First, augmentation techniques using image processing have been applied to efficiently train DNN models. Then, the advanced DNN models were fine-tuned to improve the classification accuracy and execution time. The method was evaluated on two public datasets (apple and potato leaf diseases) with accuracies of 98.08% and 99.07%, respectively.

Leaf disease detection is a crucial task in modern agriculture, aiding in early diagnosis and prevention of crop infections. In this research paper, authors present a comprehensive study comparing nine widely used pre-trained models, namely DenseNet201, EfficientNetB3, EfficientNetB4, InceptionResNetV2, MobileNetV2, ResNet50, ResNet152, VGG16, and Xception, with our newly developed custom CNN (Convolutional Neural Network) for leaf disease detection. The objective is to determine if our custom CNN can match the performance of these established pre-trained models while maintaining superior efficiency. The authors trained and fine-tuned each pre-trained model and our custom CNN on a large dataset of labeled leaf images, covering various diseases and healthy states. Subsequently, the authors evaluated the models using standard metrics, including accuracy, precision, recall, and F1-score, to gauge their overall performance. Additionally, the authors analyzed computational efficiency regarding training time and memory consumption. Surprisingly, our results indicate that the custom CNN performs comparable to the pre-trained models, despite their sophisticated architectures and extensive pre-training on massive datasets. Moreover, our custom CNN demonstrates superior efficiency, outperforming the pre-trained models regarding training speed and memory requirements. These findings highlight the potential of custom CNN architectures for leaf disease detection tasks, offering a compelling alternative to the commonly used pre-trained models. The efficiency gains achieved by our custom CNN can be beneficial in resource-constrained environments, enabling faster inference and deployment of leaf disease detection systems. Overall, our research contributes to the advancement of agricultural technology by presenting a robust and efficient solution for the early detection of leaf diseases, thereby aiding in crop protection and yield enhancement.

The use of Convolutional Neural Networks (CNNs) for image classification is wellestablished in defect detection within manufacturing environments. However, their application in assembly processes remains underexplored. This study investigates the effectiveness of using relatively smaller CNNs for detecting assembly defects by testing multiple existing pre-trained CNNs and a custom CNN on a dataset of model train seat assembly images. The dataset includes common assembly defects such as missing, rotated, and swapped parts. Despite implementing various data augmentation and image processing techniques, such as cropping, normalization, and image transforms, and making several modifications to the models, the existing techniques struggled to accurately predict defects while providing the correct rationale for their predictions. The Grad-CAM analysis revealed that the models often focused on irrelevant features, highlighting the challenges of defect detection in complex assembly environments. These findings indicate the need for more robust machine learning approaches capable of handling high levels of noise and variations typical of realworld assembly conditions. This study underscores the limitations of current CNN-based defect detection methods in uncontrolled assembly settings and the necessity for further research to develop more reliable solutions.

India's agriculture is primary occupation and it experiences a yearly loss of 35% in crop productivity due to plant-related issues. Advances in technology, such as precision agriculture and the use of Deep learning algorithms, are helping to make this possible. A number of practical and technological challenges, including dataset collecting and labelling, variability in plant leaf images, inter-class similarity, imbalanced datasets, generalization, and real-time detection, are prevalent in the challenging task of detecting plant leaf disease. The main goal of utilizing a convolutional neural network (CNN) for plant leaf disease detection is to precisely categorize images of plant leaves into categories of healthy or diseased. Depending on the particular application scenario, there could be additional goals that researchers try to accomplish with their CNN models in addition to this main one. Tomato is a widely cultivated vegetable and is an important food crop worldwide. Employing machine learning and image processing methods for detecting diseases in tomato plant leaves can be highly efficient. These techniques can be used to analyze images of tomato leaves taken in the field, and an accurate algorithm can be used to identify the presence of disease symptoms. One such approach is using Convolutional Neural Networks (CNNs) algorithm which have been trained on a dataset of images of tomato leaves with and without disease symptoms. This can be done by gathering the images of the healthy tomato leaves and the infected ones and then training a CNN model to detect the difference. The trained model can categorize new images of tomato leaves into healthy or infected, offering a quick and precise method to identify diseases in tomato plants' leaves.

Tomato is a major commercial crop that gets infected with more types of diseases. Plant diseases are easily identified by their leaves. To improve the crop yield, automatic identification, and classification of plant leaf diseases and their severity estimation is one of the research area. We performed a literature review to extract and synthesize the algorithms and features that have been used in tomato disease classification. We have selected around 50 publications for review, analyzed the methods used, and provided suggestions for further research. The traditional machine learning approach fails to extract and classify multi-class tomato diseases as there is more variance in the diseased image data. To overcome this issue, more recent research work is focused on using convolutional neural network architectures. In this paper, we have summarized major machine learning and deep learning methods that have been proposed in identifying diseases.

Plants play an essential role in the life of any living organism, human or animal, so protecting this organism from disease is an urgent necessity for the survival of living organisms. The development of science has reduced the time required to discover a disease, allowing us to detect and treat diseases early using artificial intelligence. In this scientific paper, we compared the performance of (Vgg-16, MobileNet, and ConvNext) through time and accuracy among these models. We trained these models by using transfer learning models of convolutional neural networks (CNN) to classify plant diseases (potatoes, tomatoes, and peppers). We used a dataset containing 20,639 images divided into 15 classes of different diseases, we also used the same number of parameter and the same number of layers in vgg16 and mobilenet but in convnext 24 layers.The dataset from the Kaggle site and the work environment on google colab using Python language. The results are shown vgg-16 is a high accuracy of 0.97 during the training process from convnext and mobilenet,but MobilNet is faster in the time 62s.

This composition bargains with the Tomato leaf infection discovery and classification utilizing different strategies like Convolutional Neural Network (CNN), Regions with CNN (R-CNN), Fast R-CNN and Faster R-CNN. The main issue in the agricultural sector is leaf diseases, which have an impact on crop yield and financial gain. Early detection of leaf diseases in plants is essential to prevent losses to the agricultural sector. There are several tomato leaf diseases that affect the crop's leaves, including the Mosaic virus, Early Blight, Healthy, Septoria leaf, and Bacterial spot. Using deep learning algorithms and image processing methods, we can identify the diseases in tomato leaves using developing deep learning approaches. The implementation procedures in our proposed work involves data collection, pre-processing, training, feature extraction, testing, and classification utilising the Visual Geometry Group (VGG 16) to identify damaged or healthy leaves. VGG 16 is incorporated to categorise the leaves as healthy or diseased based on the data and Regression's boundary box method is adopted. Therefore, using Faster RCNN, a model is created to identify and categorise diseases from every image of a tomato leaf that is used as an input, providing a forecast with a considerably greater degree of accuracy. We obtain an accuracy of approximately 98% after fitting the collected features into the neural network over 20 iterations.

Convolutional neural network (CNN) models have been used extensively in many image recognition tasks for their state-of-the-art performance in recent years. Researchers inspired by this success frequently prefer CNNs in the agricultural field, especially for disease detection and classification. Many CNN models have been proposed for plant leaf diseases and impressive performance results have been obtained. On the other hand, standard CNNs usually need millions of parameters in the network for computation, but it is difficult to implement them on embedded and mobile devices with limited resources. Therefore, it is important to obtain lighter models by decreasing the number of parameters in addition to the high performance of the models. In this paper, a new hybrid CNN approach based on Inception architecture and depthwise separable convolutions is proposed to reduce the number of parameters and computational cost for plant leaf disease detection and classification. Although the number of parameters is significantly reduced, the results show that the proposed approach has high accuracy performance. The proposed hybrid model has been trained and tested with k-fold cross-validation using a dataset of 50,136 images containing 30 classes from 14 different leaves, including healthy and diseased ones. The new model has achieved the best accuracy of 99.27% and an average accuracy of 99%, and provides about a 75% reduction in the number of parameters compared to the standard CNN.

Farming is the mainstream of the Indian economy. Plant leaf disease detection mainly focuses on the health of leaf plants and detecting diseases in their early stages is a tedious task. In this paper, we proposed the customized convolutional neural network (CCNN) model for predicting diseases of leaves of basil plants. We modified the traditional CNN model in a way that it deals efficiently with n-dimensional features data as well as unbalanced class data. Here, we predicted diseases of leaves of basil plants in four categories as fungal, downy mildew, fusarium wilt, and healthy. No such standard dataset is available for basil leaves so here we prepared our own 916 image dataset, and the model is trained and tested by different machine learning approaches However, CCNN has given more accurate results than other existing algorithms. The model detects diseases of leaves with an accuracy of 94.24% for four classes of basil plant leaves.

It is observed that pneumonia is the largest cause of death in toddlers. Early detection would facilitate in early treatment, hence, saving many lives. This paper intend to develop a method for automating the detection of pneumonia using chest X-rays and comparing convolutional neural network and multilevel perceptron. Custom Convolutional neural network and multi-layer perceptron were implemented on a chest X-ray dataset by Kaggle. A GUI was created that accepts the chest X-ray and predicts the presence of pneumonia and gives the congestion percentage. The model accuracy was 92.63% and 77.56% for convolutional neural network and multilayer perceptron respectively. The GUI developed gives favourable outcomes. Convolutional neural network showed better results as compared to multi-layer perceptron. Thus, the custom convolutional neural network was used for the GUI.

Multi-class classification of plant leaf diseases using a hybrid deep neural transformer system and explainable AI techniques.

In order to mitigate decreases in agricultural yield and production, the identification of diseases in plants assumes paramount importance. The agricultural sector has been employing various methodologies rooted in machine learning and image processing to address these challenges. This comprehensive analysis focuses specifically on the detection of diseases in rice plants by leveraging a diverse array of machine learning and image processing techniques with input images of infected rice plants. Furthermore, we delve into significant concepts pertaining to machine learning and image processing that aid in the identification and categorization of plant diseases. Various classification methods such as the k-Nearest Neighbor Classifier (KNN), Support Vector Machine (SVM), Probabilistic Neural Network (PNN), Genetic Algorithm (GA), and others find applications in agricultural research endeavors. The selection of an appropriate classification method assumes critical importance as the quality of the output is contingent on the input data. The classification of plant leaf diseases finds utility across multiple domains, including agriculture and biological research. This paper presents an extensive exploration of rice plant diseases, encompassing aspects such as image dataset size, preprocessing techniques, segmentation methods, and classifiers.