Paddy Leaf Disease Prediction Using Machine Learning

Abstract

The economic stability of a nation rests largely on its agricultural sector. The health of the agricultural industry hinges heavily on the ability to produce disease-free rice. Procedures and techniques that are productive and efficient in increasing harvest yield are contingent upon a number of preconditions. Agriculture, including paddy farming, is essential to human societies. Our species has an ethical obligation to safeguard agriculture's vitality and growth potential. Plant diseases have been on the rise recently, in part because of the increased use of man-made chemicals and pesticides. You can't just brush off these illnesses in crops, because they could pose a threat down the line. Sometimes it's hard to recognize certain disorders because of a lack of technical understanding. In this research, we introduce machine learning-based technique for identifying rice leaf diseases. Rice Blast, bacterial blight, and leaf smut are the three most common leaf diseases that reduce rice yields. As input, we provided visuals of the sickened leaves. Leaves will display symptoms unique to the disease the plant is suffering from if that disease is present. The data set was then trained using the machine learning algorithm SVM (Support Vector Machine) after the pre-processing was complete