Improvement Classification Approach in Tomato Leaf Disease using Modified Visual Geometry Group (VGG)-InceptionV3

This paper presents a new method for optimizing tomato leaf disease classification using Modified Visual Geometry Group (VGG)-InceptionV3. Improved performance of VGG-16 model as base with InceptionV3 block reduced the number convolution layers from 16 to 10 layers, and added an that was improved by adding layer 3 4 increase accuracy reduce parameters computation time model. The experiments were performed on leaves PlantVillage dataset classes, consisting nine classes diseased one class healthy leaves. results showed proposed able 99.27%. Additionally, approach compared state-of-the-art Convolutional Neural Network (CNN) models such VGG16, InceptionV3, DenseNet121, MobileNetV2, RestNet50. Comparative had highest in required smaller computational time.