DEEP LEARNING METHODS COMPARISON ON IMAGES OF TOMATO AND CUCUMBER LEAF IDENTIFICATION

Deep learning and image processing applications have become widespread, thanks to hardware developments and increased processing power. The use of technology in agriculture is increasing rapidly with the development of technology. One of the recent applications of technology in agriculture is image processing applications using deep learning. Image processing is aimed at sustainable agriculture. Deep learning is used in applications such as disease detection, agricultural spraying, maturity granding, irrigation, fertilization. In this study, deep learning models AlexNet and SqueezeNet are used to classify tomato and cucumber leaf images. 30 tomato leaves and 30 cucumber leaves are photographed to create the dataset used in the study. Afterwards, the images obtained are increased with data augmentation methods and a data set is created. The dataset consists of 2 classes and a total of 300 images. The data set is used 70% for training and 30% for validation. The results obtained from AlexNet and SqueezeNet deep learning models are given comparatively.