Classification of fish species with two dorsal fins using centroid-contour distance

Color, texture and shape are generally used features in order to recognise an object from an image. In this study centroid-contour distance method is used in order to classify fish species with two dorsal fins. Therefore, fish images with two dorsal fins were used from fish images database taken under specific conditions. Various image processing methods were applied on images in order to extract centroid-contour distances. These distances were used as features and Nearest Neighbour algorithm was used for classification. 15 species from 427 fish images were classified with 95% general accuracy achievement.