Projects Last Projects
Corn Plant Segmentation
Snir Homsky and Iliya Rubinchik
Supervised by Alon Zvirin and Yaron Honen
Mask R-CNN is a conceptually simple, flexible, and general framework for object instance segmentation which efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. This Project tackles the task of corn plant segmentation given a partially annotated small dataset using Mask R-CNN. We present a workflow for producing a large dataset from a small given dataset, which includes image augmentation, generation of artificial plant images, and generation of artificial images simulating real greenhouse scenes. Finally, we present results on leaf segmentation as well as whole plant segmentation, and discuss these results.
Please, see project report.
Please, see final presentation.