Feature Extraction and Machine Learning for the Classification of Brazilian Savannah Pollen Grains.

Journal: PloS one
Published Date: Jan 1, 2016

Abstract

The classification of pollen species and types is an important task in many areas like forensic palynology, archaeological palynology and melissopalynology. This paper presents the first annotated image dataset for the Brazilian Savannah pollen types that can be used to train and test computer vision based automatic pollen classifiers. A first baseline human and computer performance for this dataset has been established using 805 pollen images of 23 pollen types. In order to access the computer performance, a combination of three feature extractors and four machine learning techniques has been implemented, fine tuned and tested. The results of these tests are also presented in this paper.

Authors

  • Ariadne Barbosa Gonçalves
    Department of Biotechnology, INOVISAO, Dom Bosco Catholic University, Campo Grande, Mato Grosso do Sul, Brazil.
  • Junior Silva Souza
    Department of Computing Science, Universidade Federal de Mato Grosso do Sul, Campo Grande, Mato Grosso do Sul, Brazil.
  • Gercina Gonçalves da Silva
    Department of Environmental Science and Agricultural Sustainability, Dom Bosco Catholic University, Campo Grande, Mato Grosso do Sul, Brazil.
  • Marney Pascoli Cereda
    Department of Environmental Science and Agricultural Sustainability, Dom Bosco Catholic University, Campo Grande, Mato Grosso do Sul, Brazil.
  • Arnildo Pott
    Laboratory of Botany, Universidade Federal de Mato Grosso do Sul, Campo Grande, Mato Grosso do Sul, Brazil.
  • Marco Hiroshi Naka
    Department of Biotechnology, INOVISAO, Dom Bosco Catholic University, Campo Grande, Mato Grosso do Sul, Brazil.
  • Hemerson Pistori
    Department of Biotechnology, INOVISAO, Dom Bosco Catholic University, Campo Grande, Mato Grosso do Sul, Brazil.

Keywords

External Resources

Popular Topics
Recent Journals