Learning from Synthetic Dataset for Crop Seed Instance Segmentation
Yosuke Toda, Fumio Okura, Jun Ito, Satoshi Okada, Toshinori Kinoshita, Hiroyuki Tsuji, Daisuke Saisho
The paper trains a Mask R-CNN model for crop seed instance segmentation using synthetic data, achieving high performance on real-world datasets for barley and other crops.
bioRxiv · Dec 7, 2019 · PreprintBioinformatics