Classification for Diseases in Potatoes Leaf Using Yolov8
Аннотация
Potato leaf diseases pose a significant threat to global food security, affecting yield and quality. Accurate and efficient disease classification methods are crucial for timely intervention and crop management. This study investigates the efficacy state-of-the-art deep learning architecture, YOLOv8 for potato leaf disease classification.
The YOLOv8 architecture, renowned for its real-time object detection capabilities, is adapted for multi-class classification of potato leaf diseases. Through transfer learning, the model is pre-trained on a large-scale dataset and fine-tuned on a specific potato leaf disease dataset. YOLOv8 leverages a single-stage object detection framework, employing a series of convolutional layers to detect and classify diseases directly from images. Similarly, Vision Transformers, which have shown promising results in image classification tasks, were employed for comparison. Experimental results revealed that YOLOv8 exhibited an accuracy of 97.9%.
The dataset utilized in this research consists of high-resolution images of potato leaves affected by various diseases, including late blight, early blight, and healthy leaves. Preprocessing techniques such as data augmentation and normalization were applied to enhance model robustness and generalization. Further analysis was conducted to understand the strengths and limitations of each approach. YOLOv8 demonstrated superior performance in detecting small lesions and intricate patterns on potato leaves, owing to its object detection capabilities.
This study contributes to advancing the field of agricultural computer vision by providing insights into the performance of deep learning architectures for potato leaf disease classification. The findings offer valuable guidance for researchers and practitioners seeking to develop robust and efficient disease detection systems to support sustainable crop management practices.
The YOLOv8 architecture, renowned for its real-time object detection capabilities, is adapted for multi-class classification of potato leaf diseases. Through transfer learning, the model is pre-trained on a large-scale dataset and fine-tuned on a specific potato leaf disease dataset. YOLOv8 leverages a single-stage object detection framework, employing a series of convolutional layers to detect and classify diseases directly from images. Similarly, Vision Transformers, which have shown promising results in image classification tasks, were employed for comparison. Experimental results revealed that YOLOv8 exhibited an accuracy of 97.9%.
The dataset utilized in this research consists of high-resolution images of potato leaves affected by various diseases, including late blight, early blight, and healthy leaves. Preprocessing techniques such as data augmentation and normalization were applied to enhance model robustness and generalization. Further analysis was conducted to understand the strengths and limitations of each approach. YOLOv8 demonstrated superior performance in detecting small lesions and intricate patterns on potato leaves, owing to its object detection capabilities.
This study contributes to advancing the field of agricultural computer vision by providing insights into the performance of deep learning architectures for potato leaf disease classification. The findings offer valuable guidance for researchers and practitioners seeking to develop robust and efficient disease detection systems to support sustainable crop management practices.