Enhancing Apple Leaf Diagnosis Through Deep Learning Techniques

Apple is a type of fruit, which is very nutrient-rich and offers a variety of health advantages. They are also rich in antioxidants and fiber. Consuming them is associated with a reduced chance of developing many chronic conditions, including diabetes, a condition coronary heart disease, as well as cancer. Aside from aiding in weight loss, apples may also enhance digestive and cognitive well-being. Apple Leaf, on the other hand, has a lot of fiber and can be helpful when you're sick to increase your appetite. Apple leaf is thought to have anti-inflammatory qualities and is high in antioxidants. The methods of detecting apple leaf disease are presented in this research. It is dependent on a study that develops a CNN (Convolutional Neural Network) to categorize a completely distinct variety of apple leaf diseases. If a diseased leaf is discovered, this program will detect the type of the disease. The system in question uses cutting-edge deep learning techniques as well as transfer learning and convolutional neural networks. The outcome demonstrates the CNN model that has been retrained performs better when detecting the disease of the leaf. The conventional methods to classify leaf disease have had an accuracy ranging around 95%. Hence, to classify the leaf disease more accurately and preferably, Convolutional neural networks-based deep learning for image recognition is proposed. This is a lightweight PlantifyDr Dataset on Kaggle that serves to identify leaf photos using the DNN. With the help of VGG16, the accuracy achieved in this work is about 97.50% on the Apple Leaf Dataset. It presents good accuracy in classifying the type of disease when it is compared with many other approaches found in the literature