Contour matching for fish species recognition and migration monitoring

Abstract

A variety of matching and classification techniques have been employed in applications requiring pattern recognition. In this chapter we introduce a simple and accurate real-time contour matching technique specifically for applications involving fish species recognition and migration monitoring. We describe Fish ID, a prototype vision system that employs a software implementation of our newly developed contour matching algorithms. We discuss the challenges involved in the design of this system, both hardware and software, and we present results from a field test of the system at Prosser Dam in Prosser, Washington. In tests with up to four distinct species, the algorithm correctly determines the species with greater than 90 percent accuracy. © 2008 Springer-Verlag Berlin Heidelberg.