Abstract : Saving earth’s biodiversity for future generations is an important global task, where automatic recognition of pollen species by means of computer vision represents a highly prioritized issue. This work focuses on analysis and classification stages. A combination of geometrical measures, Fourier descriptors of morphological details using Discrete Cosine Transform (DCT) in order to select their most significant values, and colour information over decorrelated stretched images are proposed as pollen grains discriminative features. A Multi-Layer neural network was used as classifier applying scores fusion techniques. 17 tropical honey plant species have been classified achieving a mean of 96.49% ± 1.16 of success.
https://hal.inria.fr/hal-01571461
Contributeur : Hal Ifip
<>
Soumis le : mercredi 2 août 2017 - 16:22:07
Dernière modification le : mercredi 15 août 2018 - 16:40:04
Jaime Ticay-Rivas, Marcos Pozo-Baños, Carlos Travieso, Jorge Arroyo-Hernández, Santiago Pérez, et al.. Pollen Classification Based on Geometrical, Descriptors and Colour Features Using Decorrelation Stretching Method. Lazaros Iliadis; Ilias Maglogiannis; Harris Papadopoulos. 12th Engineering Applications of Neural Networks (EANN 2011) and 7th Artificial Intelligence Applications and Innovations (AIAI), Sep 2011, Corfu, Greece. Springer, IFIP Advances in Information and Communication Technology, AICT-364 (Part II), pp.342-349, 2011, Artificial Intelligence Applications and Innovations. 〈10.1007/978-3-642-23960-1_41〉. 〈hal-01571461〉
