Skip header navigation

University of Stirling

×

Conference Proceeding

Trainable n-tuple pattern classifier and its application for monitoring fish underwater

Citation
Chan D, Hockaday S, Tillett RD & Ross L (1999) Trainable n-tuple pattern classifier and its application for monitoring fish underwater. In: Seventh International Conference on Image Processing And Its Applications, 1999. IEE Conference Publication, 465. Seventh International Conference on Image Processing And Its Applications, 1999., Manchester, 13.07.1999-15.07.1999. Piscataway, NJ: IEE, pp. 255-259. http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=791391&abstractAccess=no&userType=inst

Abstract
This paper describes a non-intrusive method for monitoring salmon stock. Biomass of individual salmon can be estimated remotely using salmon morphology and an underwater stereo imaging system. Salmon lateral length measurement could be measured by fitting a model to the fish in stereo images. However, the model fitting algorithm will need to be initiated manually by the user. Therefore an image processing technique that utilises a trainable n-tuple pattern recognition algorithm is under investigation. Provisional results of using the technique on a set of underwater salmon images are promising. Further experiment results show that the technique offers a fast and simple option for image segmentation and fish recognition in underwater images.

StatusPublished
Author(s)Chan, Dickson; Hockaday, S; Tillett, Robin D; Ross, Lindsay
Title of seriesIEE Conference Publication
Number in series465
Publication date31/12/1999
Publication date online31/07/1999
PublisherIEE
Publisher URLhttp://ieeexplore.ieee.org/…no&userType=inst
Place of publicationPiscataway, NJ
ISSN of series0537-9989
ISBN0-85296-717-9
ConferenceSeventh International Conference on Image Processing And Its Applications, 1999.
Conference locationManchester
Dates
Scroll back to the top