Fruit Recognition and Classification with Deep Learning Support on Embedded System (fruitnet)


Unal H. B. , Vural E., Savas B. , BECERİKLİ Y.

2020 Innovations in Intelligent Systems and Applications Conference, ASYU 2020, İstanbul, Türkiye, 15 - 17 Ekim 2020 identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası:
  • Doi Numarası: 10.1109/asyu50717.2020.9259881
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye

Özet

© 2020 IEEE.The fruit classification process is commercially important. Fruit production at harvest time is quite high. Classification of fruits according to their types and characteristics is usually done by hand and eye. This method can cause huge losses in terms of time, cost and labor. In the proposed study, fruit recognition is carried out by using image processing methods. In the study, the classification process Convolutional Neural Networks (ConNN)∗ deep learning model is made. The proposed model is developed on Keras platform. For the realization of the study in real life, 20 different fruits in 2 different data sets are tested. The last designed model is tested on Jetson Nano card in real time.∗Convulational Neural Network has been abbreviated as ConNN, not CNN or CoNN, CNN has been used as the abbreviation of Celluar Neural Network and CoNN has been used as the abbreviation of Cooperative neural networks in the literature as a long time.