Sustainable Agriculture: A Approach For Rice Leaf Disease Detection And Classification Using Dcnn And Enhanced Datasets

Abstract

The Quality And Productivity Of Rice Crops Can Be Significantly Impacted By A Variety Of Diseases. For Effective Management And Higher Agricultural Productivity, Early Disease Detection And Classification Are Essential. The Primary Objective Of This Study Is To Classify Rice Leaf Illnesses From Visual Data Using Convolutional Neural Networks (CNNs). The Collection Contains Images Of Both Healthy And Diseased Rice Leaves Categorized Into Classes Including Hispa, Brown Spot, And Leaf Blast. Scaling And Normalizing Are Two Of The Many Picture Preparation Techniques Used To Enhance Model Performance. The CNN Model Is Trained To Identify Patterns In Leaf Pictures, Enabling Accurate Disease Classification. By Using Deep Learning Techniques To The Development Of Automated And Efficient Disease Detection Systems, This Strategy Aims To Reduce Reliance On Manual Inspection And Promote Sustainable Agricultural Practices.

Keywords