Classification of honeybee pollen using a multiscale texture filtering scheme

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.

[1]  Jian Fan,et al.  Texture Classification by Wavelet Packet Signatures , 1993, MVA.

[2]  Josef Kittler,et al.  Floating search methods in feature selection , 1994, Pattern Recognit. Lett..

[3]  Robert M. Hodgson,et al.  Texture Measures for Carpet Wear Assessment , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Linda G. Shapiro,et al.  Computer and Robot Vision , 1991 .

[5]  I. Daubechies.  Orthonormal bases of compactly supported wavelets , 1988 .

[6]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[7]  D. Hodges.  The pollen loads of the honey bee: a guide to their identification by colour and form. , 1984 .

[8]  E. Diaz,et al.  Etude de la couleur du pollen apicole recueilli par Apis mellifera L. en Espagne du nord-ouest (Galice) , 1998 .

[9]  M. P. Saa-Otero,et al.  Analysis of fatty acids, proteins and ethereal extract in honeybee pollen - Considerations of their floral origin , 2000 .

[10]  M. I. Hidalgo Berutich,et al.  About some physical characteristics of the pollen loads collected by Apis mellifera L. , 1990 .

[11]  P. Carrion.  Could the pollen origin be determined using computer vision ? An experimental study , 2002 .

[12]  Kenneth I. Laws,et al.  Rapid Texture Identification , 1980, Optics & Photonics.

[13]  Ping Li,et al.  Pollen texture identification using neural networks , 1999 .

[14]  G. Erdtman.  The acetolysis method-a revised description , 1960 .

[15]  J. S. Bonvehí,et al.  Nutrient composition and microbiological quality of honeybee-collected pollen in Spain , 1997 .

[16]  Michael Unser,et al.  Multiresolution Feature Extraction and Selection for Texture Segmentation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Milan Sonka,et al.  Image Processing, Analysis and Machine Vision , 1993, Springer US.

[18]  Ludmila I. Kuncheva,et al.  A Theoretical Study on Six Classifier Fusion Strategies , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  David G. Stork,et al.  Pattern Classification , 1973 .

[20]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..