Biodiversty and math on TV

TV news enterview shows SCG's research

Plant species identification based on venation system shape analysis

Rodrigo de Oliveira Plotze

Instituto de Ciências Matemáticas e de Computação - Universidade de São Paulo, 2004

The plant species diversity makes their correct identification a very complex task. The traditional taxonomy models, associated with species biodiversity, has been transformed this task in a challenger for the researches. This work presents a new approach to plant species identification, based on internal characteristics of leaf form. The data are collected by computer vision and shape analysis techniques, which extracts features from complexity (fractal dimension) and biometry of plant species. The methodology efficiency was evaluated with real cases of species identification: digital images of Mata Atlântica and brazilian Cerrado species; and passion fruit species of genus Passiflora. The species classifications are performed using pattern recognition techniques as clustering and artificial neural networks.

keywords: biometry,feature extraction,fractal dimension,image analysis,leaf identification,taxonomy