A SOA-Based Fish Recognition System Prototype

This paper presents a new system to automatically recognize fishes based their digital pictures. The system follows the requirement of SOA (Service Oriented Architecture) in order to provide a self-service platform for public. The system provides services like the training mode, the recognition mode, and the consulting mode. These services can be deployed onto various application servers at different locations in the world and serve as the interface system of fish knowledge retrieving and collaboration. The system services utilize the previous works on fish morphological ontology construction and digital picture recognition for carps and other species. Both user and expert can upload a training fish picture and the name of the fish, the system will decompose the picture into properties and compose them into owl with the given fish name. In recognition mode the fish picture will follow the same procedure and be compared with stored features to get the fish name and then the other properties and relations. The system prototype is implemented using web services from Tomcat. The fish images and owl repository are saved in MySql database and ontologies are stored in OWL files.