Abstract

Usage of artificial intelligence and machine learning is widespread in many areas such as information technology, driverless vehicles, health technology and marketing. The remarkable upward trend in studies on data science, machine learning, data visualization, artificial intelligence and deep learning is progressing even faster today. Between the studies of leaf classification in literature, it is seen that it uses feature extraction techniques such as various distance calculations according to the marked points, curvature-based shape feature and the use of different components of the image. The variety of feature extraction techniques is effects performance and models selection. Therefore, nowadays the models are used without features such as deep learning. In this study, leaf images have been classified using CNN model. Feature training, which is one of the many advantages of deep learning, enables to achieve results without using the above mentioned approach.CNN model was created in 2 stages. First step is feature learning contain process such as convolutional layer, nonlinearity layer, pooling, convolution and relu, pooling. Classification process used structures such as flatten, fully connected and softmax steps. Each species is regarded as a label and the classified by CNN model.