Classification of honeybee pollen using a multiscale texture filtering scheme

  • Authors:
  • P. Carrión;E. Cernadas;J. F. Gálvez;M. Damián;P. de Sá-Otero

  • Affiliations:
  • Departamento de Informática, Universidade de Vigo, Campus Universitario As Lagoas, 32004 Ourense, Spain;Departamento de Informática, Universidade de Vigo, Campus Universitario As Lagoas, 32004 Ourense, Spain;Departamento de Informática, Universidade de Vigo, Campus Universitario As Lagoas, 32004 Ourense, Spain;Departamento de Informática, Universidade de Vigo, Campus Universitario As Lagoas, 32004 Ourense, Spain;Departamento de Bioloxía Vexetal e Ciencias do Solo, Universidade de Vigo, Campus Universitario As Lagoas, 32004 Ourense, Spain

  • Venue:
  • Machine Vision and Applications
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

People are interested in the composition of honeybee pollen due to its nutritional value and therapeutic benefits. Its palynological composition depends on the local flora surrounding the beehive, and its identification is currently done manually using optical microscopy. This procedure is tedious and expensive in systematic application and is unable to automatically separate pollen loads of different species of plants. We present an automatic methodology to discriminate pollen loads based on texture image classification. Texture features are generated using a multiscale filtering scheme. A statistical evaluation of the algorithm is provided and discussed.