The classification of pollen grains using texture information in combination with shape features is presented in this paper. The surface texture of pollen is characterised by using Gabor transforms, the geometric shape is described by using moment invariants, and the pollen grains are classified by an artificial neural network. In an experiment with five types of pollen grains, more than 97% of samples are correctly classified. Copyright © 2004 John Wiley & Sons, Ltd.
| Journal | Journal of Quaternary Science |
|---|---|
| Publisher | Wiley |
| Publication Date | 2004-12-01 |
| Publication Year | 2004 |
| Volume | 19 |
| Issue | 8 |
| Pages | 763-768 |
| Document Type | Journal Article |
| Print ISSN | 0267-8179 |
| eISSN | 1099-1417 |
| DOI | 10.1002/jqs.875 |
| Subject | Earth & Environmental Science |
| NARA Access Coverage | 1996-01-01~Current |
|---|---|
| Journal Homepage | https://onlinelibrary.wiley.com/loi/10991417 |
| Publisher Page | Open Publisher Page |