Identifying plant species using architectural features of leaf microscopy images

Research output: Contribution to journalArticle

Authors

  • Joao Batista Florindo
  • Odemir Martinez Bruno
  • D R Rossatto
  • R M Kolb
  • M C Gomez

Colleges, School and Institutes

External organisations

  • Oral Pathology Unit
  • University of Birmingham
  • São Carlos Institute of Physics
  • Polytechnic School of the University of São Paulo
  • Physics Institute of Sao Carlos
  • University of Sao Carlos

Abstract

This work proposes an analytical method to identify plant species based on microscopy images of the midrib cross-section of leaves. Unlike previous shape-based approaches based on the individual shape of external contours and cells, an architectural analysis is proposed, where the midrib is semi-automatically segmented and partitioned into histologically relevant structures composed of layers of cells and vascular structures. Using a sequence of morphological operations, a set of geometrical measures from the cells in each layer is extracted to produce a vector of features for species categorization. The method applied to a database containing 10 species of plants from the Brazilian flora achieved a success rate of 91.7%, outperforming other classical shape-based approaches published in the literature.

Details

Original languageEnglish
JournalBotany
Early online date21 Oct 2015
Publication statusE-pub ahead of print - 21 Oct 2015

Keywords

  • automatic species identification, image analysis, morphological features