Classification of Cabbage and Broccoli with Deep Learning Method for Robotic Harvesting Systems
Küçük Resim Yok
Tarih
2023
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Classification of cabbage and broccoli using deep learning is very important in robotic harvesting systems. Deep learning is a machine learning method that allows learning complex models using artificial neural networks and large data sets. With the help of this method, it can be used effectively in plant classification and visual recognition problems. In order to classify plants such as cabbage and broccoli, a deep learning model must first be created. For this reason, Inception_v3 image recognition and classification modelling, which is one of the deep learning methods, was used in the study. The study was carried out over 2 classes. The created classes are cabbage and broccoli. The tpu hardware accelerator provided by Google Colab was used for training the model. The number of training cycles (epoch) is 10. The learning rate of 0.001 was determined as training parameters. According to these results, it was concluded that the Inception_v3 model was successful for training the broccoli and cabbage data set. During the training process, the loss value of the model gradually decreased and the accuracy value increased. In the validation phase, which is the last phase, the loss value was 0.0005 and the accuracy value was 1.0000.
Açıklama
Anahtar Kelimeler
Deep learning, Classification, Broccoli, Description, Cabbage
Kaynak
Türk Tarım - Gıda Bilim ve Teknoloji dergisi
WoS Q Değeri
Scopus Q Değeri
Cilt
11
Sayı
9
