Memorial University DAI: Fish species identification using image analysis of echo-sounder images

advanced search

Digital Archives Initiative
Memorial University - Electronic Theses and Dissertations 3

menu off

add document to favorites : add page to favorites : reference url

back to results : previous : next

Search this object:

0 hit(s) :: previous hit : next hit

View:

previous page : next page

Document Description

Title	Fish species identification using image analysis of echo-sounder images
Author	Lefeuvre, Patricia, 1967-
Description	Thesis (M.Eng.)--Memorial University of Newfoundland, 2003. Engineering and Applied Science
Date	2002
Pagination	1 v. (various foliations) : ill., maps
Subject	Fishing surveys--Newfoundland and Labrador; Fishing surveys--Grand Banks of Newfoundland; Echo sounding in fishing--Newfoundland and Labrador; Echo sounding in fishing--Grand Banks of Newfoundland
Degree	M.Eng.
Degree Grantor	Memorial University of Newfoundland. Faculty of Engineering and Applied Science
Discipline	Engineering and Applied Science
Language	eng
Spatial Coverage	Canada--Newfoundland and Labrador Grand Banks of Newfoundland
Notes	Includes bibliographical references.
Abstract	Acoustic surveys for marine fish in coastal waters typically involve identification of species groups. Incorrect classification can limit the usefulness of both distribution and biomass estimates. Fishing catch data can assist in identification, but are rarely spatially comparable to acoustic data and are usually biased by gear type. This thesis describes a technique and a software toolkit, "FASIT" (Fisheries Assessment and Species Identification Toolkit), developed by the author to enable automated identification of Atlantic cod (Gadus morhus), capelin (Mallotus villosus), and redfish (Sebastes spp.) based on high resolution acoustic imaging offish aggregations. The approach has been to assess and analyze various amplitude, shape and location features of the acoustic returns from shoals and individual fish, then to use these features to develop algorithms which discriminate among species. Fourteen classifiers based on Three-Nearest Neighbour classification and Mahalanobis distance classification have been implemented and tested. The best classifier had an average correct classification rate of 96.8%. The data used for this thesis are fisheries data from a number of Newfoundland bays and the Grand Bank region collected using a 38 KHz digital echo- sounder.
Type	Text
Resource Type	Electronic thesis or dissertation
Format	Image/jpeg; application/pdf
Source	Paper copy kept in the Centre for Newfoundland Studies, Memorial University Libraries
Local Identifier	a1614905
Rights	The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission.
Collection	Electronic Theses and Dissertations
Scanning Status	Completed
PDF File	(15.96 MB) -- http://collections.mun.ca/PDFs/theses/Lefeuvre_Patricia.pdf
CONTENTdm file name	87605.cpd