Automatic identification of bird species: A comparison between kNN and SOM classifiers

Author

Kaminska, Dorota ; Gmerek, Artur

Author_Institution

Inst. of Mechatron. & Inf. Syst., Tech. Univ. of Lodz, Lodz, Poland

fYear

2012

fDate

27-29 Sept. 2012

Firstpage

77

Lastpage

82

Abstract

This paper presents a system for automatic bird identification, which uses audio input. The experiments have been conducted on three groups of birds, which were created basing finishing on classification, the system is fully automated. The main problem in automatic bird recognition (ABR) is the choice of proper features and classifiers. Identification has been made using two classifiers-kNN (k Nearest Neighbor) and SOM (Self Organizing Maps). System has been tested using data extracted from natural environment.

Keywords

audio recording; audio signal processing; pattern classification; self-organising feature maps; ABR; SOM classifiers; audio input; automatic bird identification; automatic bird recognition; bird species; data extraction; k nearest neighbor; kNN classifiers; natural environment; self organizing maps; Accuracy; Birds; Correlation; Feature extraction; Hidden Markov models; Mel frequency cepstral coefficient; Training; HMM; SOM; birds; identification; kNN; recognition; self organizing maps;

fLanguage

English

Publisher

ieee

Conference_Titel

New Trends in Audio & Video and Signal Processing: Algorithms, Architectures, Arrangements, and Applications (NTAV/SPA), 2012 Joint Conference

Conference_Location

Lodz

Print_ISBN

978-8-3728-3502-4

Type

conf

Filename

7085515