Published March 5, 2021 | Version 1.0

Colorado State University Geometric Snowflake Classification Dataset

  • 1. Colorado State University

Description

This dataset contains over 25,000 human-classified images of snowflakes sorted into the following categories:

AG (aggregate)

CC (columnar crystal)

GR (graupel)

PC (planar crystal)

SP (small particle)

Filenames are in the following format:

YYYY.MM.DD_HH.MM.SS_flake_X_cam_Y_candidate_Z.png

YYYY.MM.DD_HH.MM.SS: datetime raw image was collected

X: trigger event

Y: MASC system camera index that produced raw image

Z: detection index in raw image (multiple flakes are detected in most raw images)

We request that all users of this dataset reference this Zenodo entry and the accompanying JTECH paper:

Key, C. et al. (2021) Advanced Deep Learning-Based Supervised Classification of Multi-Angle Snowflake Camera Images, JTECH

Notes

This dataset may be augmented in the future with additional classes and images.

Files

!final_paper_sets.zip

Files (66.9 MB)

Name Size Download all
md5:f674fadb14ffe74f4aff37cf97a92a4a
66.9 MB Preview Download

Additional details

References

  • Key, C. et al. (2021) Advanced Deep Learning-Based Supervised Classification of Multi-Angle Snowflake Camera Images, JTECH