Building shape and texture models of diatoms for analysis and synthesis of drawings and identification

Hicks, Yulia Alexandrovna ORCID: https://orcid.org/0000-0002-7179-4587, Marshall, Andrew David ORCID: https://orcid.org/0000-0003-2789-1395, Martin, Ralph Robert, Rosin, Paul L. ORCID: https://orcid.org/0000-0002-4965-3884, Droop, Stephen J. M. and Mann, David G. 2004. Building shape and texture models of diatoms for analysis and synthesis of drawings and identification. Presented at: Irish Machine Vision and Image Processing Conference, Dublin, 1-3 Sept 2004.

Preview

PDF Download (192kB) | Preview

Abstract

We describe tools for automatic identification of diatoms by comparing their photographs with other photographs and drawings, via a model. Identification of diatoms, i.e. assigning a new specimen to one of the known species, has applications in many disciplines, including ecology, paleoecology and forensic science. The model we build represents life cycle and natural variation of both external shape and internal texture over multiple species and is based on principal curves. The model is also suitable for automatically producing drawings of diatoms at any stage of their life cycle development. Similar drawings are traditionally used for diatom identification, and encapsulate visually salient diatom features. In this article we describe the methods used to analyse photographs and drawings, present our model of diatom shape and texture variation, and illustrate our approach with a collection of drawings synthesised from our model and derived from example photographs. Finally, we present the results of identification experiments using photographs and drawings.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics Engineering
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software
Uncontrolled Keywords:	Classification ; automatic drawing synthesis ; principal curves ; diatoms.
Last Modified:	17 Oct 2022 09:41
URI:	https://orca.cardiff.ac.uk/id/eprint/5166

Citation Data

Actions (repository staff only)

Edit Item