Identifying plant species using architectural features in leaf microscopy images

Authors
Florindo, Joao Batista; Bruno, Odemir Martinez; Rossatto, Davi Rodrigo; Kolb, Rosana Marta; Gómez, María Cecilia; Landini, Gabriel
Publication Year
2016
Language
English
Format
article
Status
Published version
Description
This work proposes an analytical method to identify plant species based on microscopy images of the midrib cross-section of leaves. Unlike previous shape-based approaches based on the individual shape of external contours and cells, an architectural analysis is proposed, where the midrib is semi-automatically segmented and partitioned into histologically relevant structures composed of layers of cells and vascular structures. Using a sequence of morphological operations, a set of geometrical measures from the cells in each layer is extracted to produce a vector of features for species categorization. The method applied to a database containing 10 species of plants from the Brazilian flora achieved a success rate of 91.7%, outperforming other classical shape-based approaches published in the literature.
Fil: Florindo, Joao Batista. Universidade de Sao Paulo; Brasil
Fil: Bruno, Odemir Martinez. Universidade de Sao Paulo; Brasil
Fil: Rossatto, Davi Rodrigo. Universidade Estadual Paulista Julio de Mesquita Filho; Brasil
Fil: Kolb, Rosana Marta. Universidade Estadual Paulista Julio de Mesquita Filho; Brasil
Fil: Gómez, María Cecilia. Universidad Nacional del Litoral; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe; Argentina
Fil: Landini, Gabriel. University Of Birmingham; Reino Unido
Subject
AUTOMATIC SPECIES IDENTIFICATION
IMAGE ANALYSIS
MORPHOLOGICAL FEATURES
Ciencias de la Computación
Ciencias de la Computación e Información
CIENCIAS NATURALES Y EXACTAS
Ciencias de las Plantas, Botánica
Ciencias Biológicas
CIENCIAS NATURALES Y EXACTAS
Access level
Restricted access
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repository
CONICET Digital (CONICET)
Institution
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identifier
oai:ri.conicet.gov.ar:11336/17501