Tea Leaf Disease Detection and Classification Using CNN, SVM and Dense Net

Tea is one of the most extensively consumed potables encyclopedically, and the health and quality of tea leaves play a pivotal part in the tea assiduity. The periodic tea product has been dropped due to the goods of multitudinous conditions, including tea splint scar, tea late scar, tea early scar, and tea algae splint spot. Tea splint affections can also lower the quality of tea and cost tea growers a lot of plutocrats. To drop product losses, enhance tea quality, and boost tea planter income, accurate discovery and identification of tea splint conditions as well as prompt forestallment and control measures are pivotal. Detecting conditions in tea leaves at an early stage is vital to help crop losses and maintain tea product. In recent times, machine literacy algorithms have shown promising results in automating complaint discovery processes. This study aims to develop a robust complaint discovery system for tea leaves using Convolutional Neural Networks (CNN), Support Vector Machines (SVM), and Dense Net algorithms.