Honeybee Pollen

This dataset includes inputs which are texture features extracted from images of honeybee pollen loads captured by a stereomicroscope conected to a digital camera. The classes are the plant species: Cytisus, Castanea, Quercus, Rubus and Raphanus. The dataset has:

• 2600 instances
• 70 inputs
• 5 classes

The data are in the file honeybee_pollen.dat. Each input is standarized with mean zero and standard deviation one. The file partitions.dat includes 10 groups of 3 lines, each group associated to a random partition of the available data. The first line in each group contains the indices of the training patterns (50% of the patterns); the second line contains the indices of the validation patterns (25% of the patterns); the third line contains the indices of the test patterns (25% of the patterns).

Reference

@article{carrion04,
author = "{Carri\'on, P, and Cernadas, E. and G\'alvez, J.F. and S\'a-Otero, P.}",
title = "{Classification of honeybee pollen using a multiscale texture filtering scheme}",
journal = "{Machine Vision and applications}",
volume = "15",
pages = "186—193",
year = "2004"
}

License

This work is licensed under a Creative Commons Attribution 4.0 International License.

You can use this dataset on your publication as long as you include a citation to the reference on this page. When including a link to this dataset, please use this page instead of linking the file directly.