"Deep learning to do quality analysis of sugarcane"
Dataset with 3 sugarcane varieties to compare the precision and processing time of different CNN models. The images of each variety are separated in images of damaged sugarcane billets or images of good sugarcane billets. Each sugarcane billet was captured in high resolution images and they were segmented.
If you download or use this dataset you should cite the paper: Moises Alencastre-Miranda, Richard M. Johnson, Hermano Igo Krebs. "Convolutional Neural Networks and Transfer Learning for Quality Inspection of Different Sugarcane Varieties". To be published in IEEE Transactions on Industrial Informatics, early access publication in May 2020.
You can get the paper at: https://ieeexplore.ieee.org/document/9085904
The 77 Lab, Department of Mechanical Engineering, MIT.