Bird species classification using visual and acoustic descriptors
Year: 2016
Type: dissertation
Abstract: This work aims at presenting a system for automatic bird species classification based on acoustic and visual features extracted from the birdsong. The texture features were extracted using: Local Binary Pattern (LBP), Local Phase Quantization (LPQ), Robust Local Binary Pattern (RLBP) Gray-Scale Level Co- currence Matrix (GLCM) and Gabor filters. The acoustic characteristics are in turn extracted through the descriptors: Rhythm Histogarm (RH), Rhythm Patterns (RP) and Statistical Spectrum Descriptor (SSD.) Aiming to perform more fare comparisons, the experiments performed were made over a similar database used in the work Automatic Bird Species Identification for Large Number of Species (Lopes et al., 2011a). In the classification step, SVM classifier was used and the final results were taken by using 10-fold cross validation.
Author: Lucio, Diego Rafael
Language: Portuguese
Topic: Music and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7120407633