An Automated Local Binary Pattern Ship Identification Method by Using Sound

Abstract

Sound classification is one of the most important areas of research for mechanics and applied computersciences. Using the sound classification method, many biometric applications/methods have been presented inthe literature. This study presents a ship identification method using sounds. The method presented here isvery simple and effective. It has only two fundamental phases and these are feature extraction by onedimensional binary pattern (1D-BP) and classification with conventional classifiers phases. 1D-BP extracts256 features from each sound and these sounds are forwarded to classifiers. To test this ultra-lightweightsound identification method, a ship sounds dataset was collected from YouTube. According to our results, thismethod achieved a 97% classification accuracy. This result clearly demonstrates the merits of the 1D-BP basedon ship sound classification method and the sound-based ship identification method which we present here.