PADDY CARE: DETECTION OF PADDY PLANT LEAF DISEASE USING YOLOV8

Abstract [English]

Paddy is the most significant crop utilized by more than 2.6 billion people. Paddy leaf infections are a common hazard to rice production, affecting many farmers all over the world. Paddy Plant diseases are a severe threat to the entire production. However, plant disease diagnosis through observation of the plant leaves is a very complex work. Even experienced farmers are often unable to successfully identify certain plant diseases, leading to wrong conclusions and treatment methods. Thus, the traditional method of identifying crop diseases by visual observation is no longer suitable for modern agriculture. In the widespread application of various machine learning techniques, recognition time consumption and accuracy remain the main challenges in moving agriculture toward industrialization. Therefore, it is essential for farmers to effectively deal with them and check them with the help of timely prevention. Classifying the severity of crop diseases are the requirement for formulating disease prevention and control strategies. Early detection and treatment of rice leaf infection are critical for promoting healthy rice plant growth and ensuring adequate supply for the fast-growing population. Therefore, automatic and accurate diagnosis of plant diseases plays an essential role in ensuring high yield and quality. This research work attempts to create a simple and best model for Paddy leaf disease detection using deep learning model based on the Convolutional Neural Network (CNN) and Yolo v8. Yolo v8 is used to detect the disease part and Convolutional Neural Network used to categorize and analyzing the leaf condition that would be diseased and non-diseased. Using the Preventive Knowledge Solution, the farmers can get the preventive measures to protect the crop from the disease. And also this research work recommends the pesticides and fertilizers to defeat the identified paddy leaf disease. This model is able to differentiate and successfully detect the rice leaf diseases. The developed model utilizes epochs: 100. The experimental results show that the deep learning model created with 100 epochs has shown the best performance with precision, recall, and mAP value of 1.00, 0.94, and 0.62, respectively. At the same time, the advantages in terms of accuracy and computational cost can meet the needs of agricultural industrialization.