Edinburgh Research Explorer

Underwater Live Fish Recognition Using a Balance-Guaranteed Optimized Tree

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Related Edinburgh Organisations

Open Access permissions

Open

Documents

http://dx.doi.org/10.1007/978-3-642-37331-2_32
Original languageEnglish
Title of host publicationComputer Vision – ACCV 2012
Subtitle of host publication11th Asian Conference on Computer Vision, Daejeon, Korea, November 5-9, 2012, Revised Selected Papers, Part I
EditorsKyoung Mu Lee, Yasuyuki Matsushita, James M. Rehg, Zhanyi Hu
PublisherSpringer-Verlag GmbH
Pages422-433
Number of pages12
ISBN (Electronic)978-3-642-37331-2
ISBN (Print)978-3-642-37330-5
DOIs
Publication statusPublished - 2013

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin / Heidelberg
Volume7724
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Abstract

Live fish recognition in the open sea is a challenging multi-class classification task. We propose a novel method to recognize fish in an unrestricted natural environment recorded by underwater cameras. This method extracts 66 types of features, which are a combination of color, shape and texture properties from different parts of the fish and reduce the feature dimensions with forward sequential feature selection (FSFS) procedure. The selected features of the FSFS are used by an SVM. We present a Balance-Guaranteed Optimized Tree (BGOT) to control the error accumulation in hierarchical classification and, therefore, achieve better performance. A BGOT of 10 fish species is automatically constructed using the inter-class similarities and a heuristic method. The proposed BGOT-based hierarchical classification method achieves about 4% better accuracy compared to state-of-the-art techniques on a live fish image dataset.

Download statistics

No data available

ID: 11316273