Cotton Leaf Disease Prediction Using Transfer Learning

Cotton is one of the financially significant agricultural items in India, but it is exposed to different constraints in the leaf area. Mostly, these constraints are identified as diseases that are hard to detect with bare eyes. This study focused to develop a model to boost the detection of cotton leaf disease and pests using the deep learning technique. Basically here we did comparative study of own defined convolution neural network architecture and popular state of art CNN architecture. This study centered to foster a model to classify diseased and fresh Cotton plant and leaf using Deep Learning techniques.. For this exploration, almost 2400 examples (600 pictures in each class) were gotten to for the purpose of preparing. This created model is carried out utilizing python form 3.7.3 and the model is prepared on the profound learning bundle called Keras, TensorFlow supported, and Jupyter which are utilized as the formative climate. This model accomplished 96.4% accuracy of recognizing diseased and fresh cotton plant and leaf using transfer learning techniques.