Normalization of Active Appearance Models for Fish Species IdentificationReport as inadecuate

Normalization of Active Appearance Models for Fish Species Identification - Download this document for free, or read online. Document in PDF available to download.

ISRN Signal ProcessingVolume 2011 2011, Article ID 103293, 16 pages

Research ArticleDepartment of Information Processing, Tokyo Institute of Technology, Nagatsuta-Cho, Midori-Ku, Yokohama, Kanagawa 226-850, Japan

Received 12 January 2011; Accepted 7 February 2011

Academic Editors: C.-M. Kuo and L. Shen

Copyright © 2011 Charles-Henri Quivy and Itsuo Kumazawa. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


In recent years, automatic visual coral reef monitoring has been proposed to solve the demerits of manual monitoringtechniques. This paper proposes a novel method to reduce the computational cost of the standard Active AppearanceModel AAM for automatic fish species identification by using an original multiclass AAM. The main novelty isthe normalization of species-specific AAMs using techniques tailored to meet with fish species identification. Shapemodels associated to species-specific AAMs are automatically normalized by means of linear interpolations and manualcorrespondences between shapes of different species. It leads to a Unified Active Appearance Model built fromspecies that present characteristic texture patterns. Experiments are carried out on images of fish of four differentfamilies. The technique provides correct classification rates up to 92% on 5 species and 84.5% on 12 species and ismore than 4 times faster than the standard AAM on 12 species.

Author: Charles-Henri Quivy and Itsuo Kumazawa



Related documents