Automatic leaf structure biometry: computer vision techniques and their applications in plant taxonomy

摘要

This paper proposes a new methodology to extract biometric features of plant leafudstructures. Combining computer vision techniques and plant taxonomy protocols, theseudmethods are capable of identifying plant species. The biometric measurements are concentratedudin leaf internal forms, specifically in the veination system. The methodologyudwas validated with real cases of plant taxonomy, and eleven species of passion fruit of theudgenus Passiflora were used. The features extracted from the leaves were applied to theudneural network system to perform the classification of species. The results showed to beudvery accurate in correctly differentiating among species with 97% of success. The computerudvision methods developed can be used to assist taxonomists to perform biometricudmeasurements in plant leaf structures.