In a multi-disciplinary research work between computer science and biology, this paper assesses image analysis techniques as automatic identifiers of three Anastrepha species of quarantine importance, Anastrepha fraterculus (Wiedemann), Anastrepha obliqua (Macquart), and Anastrepha sororcula Zucchi, based on wing and aculeus images.
The right wing and aculeus of 100 individuals of each species were mounted on microscope slides, and images were captured with a stereomicroscope and light microscope. Using a SVM classifier, average accuracies of 94 and 95% were obtained based on wing and aculeus images, respectively. These results are comparable to previous identification results based on morphometric techniques and to the results achieved by experienced entomologists.
P. Perre , F. A. Faria, L. R. Jorge, A. Rocha, R. S. Torres, M. F. Souza-Filho, T. M. Lewinsohn, R. A. Zucchi. Toward an Automated Identification of Anastrepha Fruit Flies in the fraterculus group (Diptera, Tephritidae). Neotropical Entomology Journal. 2016. Doi: 10.1007/s13744-016-0403-0