Comparative Analysis of Disease Detection Among Tomato Plants Using Machine and Deep Learning Techniques

Plant diseases pose a major brat to husbandry and cause yearly crop losses. Although there is an all-encompassing hunt on the contactability of plant diseases as well as modern day methods often lacked the accuracy, efficiency and productiveness required for early diagnosis. To this end, this clause introduces new auto learning and deep learning models to improve the truth and speed of plant pyknotic diagnosis. By analyzing 40 existing studies on clear cut plants, including potatoes, tomatoes, corn and bananas, our proposed commercial aims to bridge the gap between engineering and agriculture. Our efficacious model increases contactable truth by a median of 15% and reduces processing time by 30% as well as thus facilitating early pyknotic contactability and increasing the efficiency of crop management. These advances not only benefited farmers by providing them with authorized tools to Saran crop health.but also contributed to rural productivity. Our hunt has the ability to improve rural productivity by up to 20% by optimizing yields and reducing losses, thereby solving food credentials issues and promoting permaculture practices. Of the three models that had been trained, Convolutional Neural Network CNN, +-SVM, and YOLO NAS, the CNN model achieves an astonishing truth of 96.7%. In the meantime, the SVM model attains a truth of 90.4%, while the YOLO NAS model displays an astonishing truth rate of 70.34%.