Learning computationally efficient approximations of complex image segmentation metrics

6 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Finely-grained annotated datasets for image-based plant phenotyping (2016, background): “…criteria: Typical criteria such as precision and recall are suggested and those not penalizing small local mis-alignment, which are suited for evaluating performance of boundaries between leaves, e.g., the MHD (Section 3.3.2) and its learning-based simpliﬁcation in Minervini et al. (2013).”
Annotated Image Datasets of Rosette Plants (2014, methodology): “Finally, in [18] we explore efficient approximations of complex image segmentation metrics, that could be adopted at the sensor.”