Dissertation/Thesis Abstract

SharkID: A Framework for Automated Individual Shark Identification
by Coleman, Taina Gariglio Dias, M.S., California State University, Long Beach, 2020, 40; 27834185
Abstract (Summary)

Recent progress in animal biometrics has revolutionized wildlife research. Cutting-edge techniques allow researchers to track individuals through noninvasive methods of recognition that are not only more reliable, but also applicable to large, hard-to-find, and otherwise difficult to observe animals. In this thesis, we propose a framework for automated individual shark identification based on semantic segmentation, boundary descriptors and bipartite perfect matching applied to shark dorsal fins. In order to identify a shark, we first apply semantic segmentation to extract the dorsal fin of the input source, then transform the fin’s contour to a normalized coordinate system so that we can analyze images of sharks regardless of orientation and scale. Finally, we propose a metric scheme that performs a minimum weight perfect matching in a bipartite graph. The experimental results show that our metric is able to identify and track individuals from visual data.

Indexing (document details)
Advisor: Moon, Ju Cheol
Commitee: Morales Ponce, Oscar, Lam, Shui
School: California State University, Long Beach
Department: Computer Engineering and Computer Science
School Location: United States -- California
Source: MAI 82/3(E), Masters Abstracts International
Source Type: DISSERTATION
Subjects: Bioinformatics, Artificial intelligence
Keywords: Biometric, Dorsal, Fin, Identification, Shark
Publication Number: 27834185
ISBN: 9798664790016
Copyright © 2020 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy
ProQuest