Classification of butterfly images with multi-scale local binary patterns

Butterflies are classified first according to their outer morphological qualities. It is required to analyze their genital characters when classification according to their outer morphological qualities is not possible. The genital characters of butterflies can be obtained using various chemical substances and methods; however, these processes can only be carried out with some certain expenses. Furthermore, the preparation of genital slides is time-consuming since it requires specific processes. In this study, a computer vision system based on local binary patterns was proposed to alternative conventional diagnostic methods for the diagnosis of butterfly species. 140 images of 14 butterfly species belonging to the family of Styridae are used. The butterfly diagnostic process was carried out by using LBP_{P, R} attributes as inputs for the ANN, SVM and LR classification methods. 100% classification was achieved with macro and micro patterns obtained with LBP_{P, R} for different values of parameter R. As a result, it was seen butterfly wings have different types of micro and macro properties, and LBP has a major advantage in identification of butterfly species.