Shape and Texture Based Classification of Fish Species

In this paper we conduct a case study of fish species classification based on shape awl texture. We consider three fish species: cod. haddock, and whiting. We derive shape and texture features from an apperance model of a set: of training data. The fish in the training images were manual outlined, and a, few features including the eye and backbone contour were also annotated. From these annotations all optimal MDL curve correspondence and a subsequent image registration were derived. We have analyzed a series of shape and texture and combined shape and texture modes of variation for their ability to discriminate between the fish types, as well as conducted a preliminary classification. In a linear discrimant analysis based of the two best; combined modes of variation we obtain a resubstitution rate of 76%.