Intelligent optical otolith classification for species recognition of bony fish

Authors:
D. Lefkaditis;G. J. Awcock;R. J. Howlett
Affiliations:
Intelligent Systems & Applied Image Processing Research Laboratories, Engineering Research Centre, University of Brighton, Moulsecoomb, Brighton, UK;Intelligent Systems & Applied Image Processing Research Laboratories, Engineering Research Centre, University of Brighton, Moulsecoomb, Brighton, UK;Fisheries Research Institute, Nea Peramos, Kavala, Greece
Venue:
KES'06 Proceedings of the 10th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part I
Year:
2006

Citing 3
Cited 0

Applied image processing

Applied image processing
Score normalization in multimodal biometric systems

Pattern Recognition
A pyramid approach to subpixel registration based on intensity

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The study of otoliths is an established method of age estimation of bony fish. It can also find interesting applications such as dietary studies by conducting species recognition on otoliths found in the stomach contents of marine animals. Moreover, they could even be sourced from geological sediments or pre-Neolithic archaeological excavations, providing useful data for palaeontology research. This paper presents work in progress to develop an alternative method of optical otolith recognition. This methodology is based on the processing and analysis of images acquired using a stereoscopic microscope fitted with a digital camera. Several configurations of neural networks are tested to conduct species recognition of bony fish.