Furnariidae Species Classification Using Extreme Learning Machines and Spectral Information

SARQUIS JUAN ANDRES; ALBORNOZ MARCELO; CESAR MARTINEZ; LEANDRO VIGNOLO

Subotica

Conferencia; IEEE 16th International Symposium on Intelligent Systems and Informatics (SISY 2018); 2018

Óbuda University, Hungary

Automatic bird species classification and identification areissues that have aroused interest in recent years. The main goals involvemore exhaustive environmental monitoring and natural resources managing.One of the more relevant characteristics of calling birds is the vocalisationbecause this allows to recognise species or identify new ones, toknow its natural history and macro-systematic relations, among others.In this work, some spectral-based features and extreme learning machines(ELM) are used to perform bird species classification. The experimentswere carried on using 25 species of the family Furnariidae that inhabitthe Paranaense Littoral region of Argentina (South America) and werevalidated in a cross-validation scheme. The results show that ELM classifierobtains high classification rates, more than 90% in accuracy, andthe proposed features overperform the baseline features.