Leaf epidermis images for robust identification of plants
by da Silva N. R. , daSilva Oliveira M. W., Antunes deAlmeida Filho H. , Souza Pinheiro L. F., Rossatto D. R., Kolb R. M., Martinez Bruno O. (2015)
Núbia Rosa da Silva1,2 , Marcos William da Silva Oliveira1,2 , Humberto Antunes de Almeida Filho2 , Luiz Felipe Souza Pinheiro3, Davi Rodrigo Rossatto4, Rosana Marta Kolb3 & Odemir Martinez Bruno1,2
1 Institute of Mathematics and Computer Science, University of São Paulo, USP, Avenida Trabalhador são-carlense, 400, 13566-590 São Carlos, São Paulo, Brazil.
2 Scientific Computing Group, São Carlos Institute of Physics, University of São Paulo, PO Box 369, 13560-970, São Carlos, SP, Brazil.
3 Department of Biological Sciences, Faculty of Sciences and Languages, Univ Estadual Paulista, UNESP. Av. Dom Antônio, 2100, 19806-900, Assis, São Paulo, Brazil.
4 Department of Applied Biology, Faculty of Agriculture and Veterinary Sciences, Univ Estadual Paulista, UNESP, Via de Acesso Prof. Paulo Donatto Castellane S/N. 14884-900, Jaboticabal, São Paulo, Brazil.
in Scientific Reports 6:25994 – DOI: 10.1038/srep25994 –
This paper proposes a methodology for plant analysis and identification based on extracting texture features from microscopic images of leaf epidermis. All the experiments were carried out using 32 plant species with 309 epidermal samples captured by an optical microscope coupled to a digital camera.
The results of the computational methods using texture features were compared to the conventional approach, where quantitative measurements of stomatal traits (density, length and width) were manually obtained. Epidermis image classification using texture has achieved a success rate of over 96%, while success rate was around 60% for quantitative measurements taken manually. Furthermore, we verified the robustness of our method accounting for natural phenotypic plasticity of stomata, analysing samples from the same species grown in different environments.
Texture methods were robust even when considering phenotypic plasticity of stomatal traits with a decrease of 20% in the success rate, as quantitative measurements proved to be fully sensitive with a decrease of 77%.
Results from the comparison between the computational approach and the conventional quantitative measurements lead us to discover how computational systems are advantageous and promising in terms of solving problems related to Botany, such as species identification.