Sharks are one of the major predators in the ocean. In particular, the great white shark is a primary threat to swimmers. This work proposes an automatic method for the recognition of deformable submerged objects (i.e. sharks) from aerial images of the coast line in an uncontrolled environment. It focuses on great white shark recognition in the surf zone of coastal areas. As the images were taken in an uncontrolled environment and the object shapes of interest are deformable, it is not easy to distinguish sharks from shark-like objects such as dolphins. In this paper, we propose two feature extraction methods that are based on the object's shape: the fish shape feature and shape profile methods. All feature extraction methods are applied to a new image database that contains aerial views of sharks and shark-like objects. The classifiers that are used in our proposed methods are the Support Vector Machine (SVM) and the feed-forward backpropagation neural network.

The great white shark is a large marine animal that is a potential threat to swimmers. There were many shark attack reports worldwide and many of the attacks happened in shallow waters. One way to reduce the incidence of shark attacks is to employ shark patrols. This is done by flying a light plane along the coast and the shark spotting is done by humans. The aim of this research is to automate this process. Gururatsakul [2] proposed a technique to recognize sharks from dolphins and shark-like objects in top-view aerial images by focusing on shape feature characteristics. This work proposes an alternate way of distinguishing sharks from dolphins and shark-like objects by considering twodimensional deformable models. A deformable model isrepresented by variables and two reference tables. These variables are optimized (deforming the model to best fit a test object) by iteratively adjusting their values to reduce the error output from the objective function. The classification of sharks from dolphins and shark-like objects is based on the best matching model. A high result of 93% on identifying sharks, dolphins, and shark-like objects has been achieved by the proposed method.