Feature selection for analyzing and retrieving fish otoliths using elliptic Fourier descriptors of shapes

Abstract

This paper analyzes the characteristics of an experimental otolith retrieval system based on image contours described with Elliptical Fourier Descriptors (EFD). Otoliths are found in the inner ear of fish. Their shape can be analyzed to determine sex, age, populations and species, and thus they can provide necessary and relevant information for ecological studies. The system we propose was tested by identifying three different species, Engraulis encrasicolus from the family Engraulidae, Pomadasys incisus from the family Haemulidae, and two populations of the species Merluccius merluccius (from Catalonia and Galicia) from the family Merlucciidae. We focus on the search engine, experimenting with two cases and analyzing the feature selection obtained with the EFD coefficients.