Common carp individual identification

General protocol for the image based identification of individuals within close group of common carp speciesThe aim of this study was to verify the possibility of using fully-automatic non-invasive photo-identification of individual fish based on natural marks on the fish’s body without any obvious skin patterns. This approach is an alternative to stressful invasive tagging and marking techniques. Scale patterns on the body and operculum were used as discriminative features for the identification of individuals in a closed group of fish. We used common carp Cyprinus carpio. The identification method was tested on four experimental data sets: separate short-term data set (pattern variability test) and four long-term data sets (pattern stability test) common carp (32 individual fish). The accuracy of classification was 100% in both the short-term and long-term experiments. According to these results, the methods used for automatic non-invasive image-based individual-fish identification can also beused for fish species without obvious skin patterns. Four rounds of data collection were performed over the four-month experiment for carp identification. Images were taken of the whole fish out of water. Each fish was caught in the cultivation tank, anesthetized in a bucket using clave oil, and moved to the green background for imaging. A single-layer white-fabric photographic tent with controlled illumination was used for photography. The fish heads were oriented to the left for all images. Fish were tagged for long term ID. Uploaded files 01,02,03,04 are the original files (4 datasets) and in processed there are all processed files for four datasets.