Kerem Yıldırır

Projects

Plant Disease Identification

Posted:

Abstract Detection of plant diseases via computer vision based systems are being used to identify plant diseases promptly, to prevent the spread of the disease. In this work, we present a system for classifying plant diseases from photographs of the diseased parts of the plant. The system is trained using transfer learning on convolutional neural networks (VGGNet) which are trained to classify 38 plant diseases or 11 disease classes. 95.09% average accuracy was obtained on plant-disease classification using PlantVillage dataset. Read more...

Plant Identification with Deep Learning Ensembles

Posted:   |   Categories: lorem   |   Tags: ipsum, latin, test-tag

Abstract This work describes the plant identification system that we submitted to the ExpertLifeCLEF plant identification campaign in 2018. We fine-tuned two pre-trained deep learning architectures (SeNet and DensNetwork) using images shared by the CLEF organizers in 2017. Our main runs are 4 ensembles obtained with different weighted combinations of the 4 deep learning architectures. The fifth ensemble is based on deep learning features but uses Error Correcting Output Codes (ECOC) as the ensemble. Read more...