Deep Learning Based Automated Detection of Diseases from Apple Leaf Images

In Agriculture Sciences, detection of diseases is one the most challenging tasks. The mis-interpretations plant often lead to wrong pesticide selection, resulting in damage crops. Hence, automatic recognition at earlier stages important as well economical for better quality and quantity fruits. Computer aided (CAD) has proven a supportive tool disease classification, thus allowing identification reducing rate degradation fruit quality. this research work, model based on convolutional neural network with 19 layers been proposed effective accurate classification Marsonina Coronaria Apple Scab from apple leaves. For this, database 50,000 images acquired by collecting leaves farms Himachal Pradesh (H.P) Uttarakhand (India). An augmentation technique performed dataset increase number increasing accuracy. performance analysis compared new two Convolutional Neural Network (CNN) models having 8 9 respectively. also standard machine learning classifiers like support vector machine, k-Nearest Neighbour, Random Forest Logistic Regression models. From experimental results, it observed that outperformed other CNN an accuracy 99.2%.