Image analysis methods on fish recognition

The aim of study is creating a new database which contains fish species and classifying this fish species. A new fish database was created by using the fish photos in seas of Turkey. The new feature set are obtained by marking the biometric points on fish to identify family and species of fishes. The features were obtained by using the three different biometric measurement techniques (Euclidean network technique, quadratic network technique, triangulation technique). A classifications system was created by using Naive Bayesian classifier. The obtained accuracy is 93.10% for 7 families on family classification and 75.71% for 15 species on species classification.