Normalization of Active Appearance Models for Fish Species Identification
Joint Authors
Quivy, Charles-Henri
Kumazawa, Itsuo
Source
Issue
Vol. 2011, Issue 2011 (31 Dec. 2011), pp.1-16, 16 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2011-06-23
Country of Publication
Egypt
No. of Pages
16
Main Subjects
Electronic engineering
Information Technology and Computer Science
Abstract EN
In recent years, automatic visual coral reef monitoring has been proposed to solve the demerits of manual monitoring techniques.
This paper proposes a novel method to reduce the computational cost of the standard Active Appearance Model (AAM) for automatic fish species identification by using an original multiclass AAM.
The main novelty is the normalization of species-specific AAMs using techniques tailored to meet with fish species identification.
Shape models associated to species-specific AAMs are automatically normalized by means of linear interpolations and manual correspondences between shapes of different species.
It leads to a Unified Active Appearance Model built from species that present characteristic texture patterns.
Experiments are carried out on images of fish of four different families.
The technique provides correct classification rates up to 92% on 5 species and 84.5% on 12 species and is more than 4 times faster than the standard AAM on 12 species.
American Psychological Association (APA)
Quivy, Charles-Henri& Kumazawa, Itsuo. 2011. Normalization of Active Appearance Models for Fish Species Identification. ISRN Signal Processing،Vol. 2011, no. 2011, pp.1-16.
https://search.emarefa.net/detail/BIM-446555
Modern Language Association (MLA)
Quivy, Charles-Henri& Kumazawa, Itsuo. Normalization of Active Appearance Models for Fish Species Identification. ISRN Signal Processing No. 2011 (2011), pp.1-16.
https://search.emarefa.net/detail/BIM-446555
American Medical Association (AMA)
Quivy, Charles-Henri& Kumazawa, Itsuo. Normalization of Active Appearance Models for Fish Species Identification. ISRN Signal Processing. 2011. Vol. 2011, no. 2011, pp.1-16.
https://search.emarefa.net/detail/BIM-446555
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-446555