Ülkesel ekmeklik buğday alımı için derin öğrenme tabanlı buğday sınıflandırma

Within the scope of the thesis study, the reflectance values of 24 different wheat species were measured using the Near-Infrared (NIR) Spectrometer device and used as input parameters in machine learning and deep learning approaches to classify wheat species. These approaches were compared with each other, and the results were evaluated. As a result of the approaches discussed, it has been seen that machine learning techniques do not show sufficient performance to distinguish between reflectance value and species. When classification is made with the deep learning model, higher accuracy values have been achieved than machine learning algorithms. The deep learning approach has been handled separately to classify with direct reflectance data and classify images created from reflectance data.