Altuntas, YahyaKocamaz, Adnan FatihYeroglu, Celaleddin2024-08-042024-08-042019https://doi.org/10.1109/idap.2019.8875906https://hdl.handle.net/11616/99039International Conference on Artificial Intelligence and Data Processing (IDAP) -- SEP 21-22, 2019 -- Inonu Univ, Malatya, TURKEYApricot variety identification is an important issue for both plant breeders, seedling producers and conservation of biodiversity. Leaf, which contains important information about the plant to which it belongs, is used for species identification and plant disease diagnosis as well as for variety identification. In this study, the possibilities of identification of apricot varieties were investigated by using leaf characteristics. Within the scope of the study, a dataset consisting of 339 leaf images belonging to 10 apricot varieties was created. The proposed method consists of 3 main steps. In the segmentation step, the leaves were segmented from the background. 12 digital morphological features were obtained by using apricot leaf characteristics in the feature extraction step. In the classification step, the obtained feature vector was classified using the k-nearest neighbor classifier. 10-fold cross-validation method was used to determine classifier performance. The overall accuracy of the proposed method was measured as 79.05%.trinfo:eu-repo/semantics/closedAccessapricot varieties identificationleaf classificationimage processingKNNConference Object10.1109/idap.2019.88759062-s2.0-85074890222N/AWOS:000591781100037N/A