A fish population counting method using fuzzy artificial neural network

A new method to efficiently get fish count using digital picture and fuzzy artificial neural network is presented. The new method can handle overlapped fishes, as well as different sized fishes. The intelligent window over the digital picture based on neural network feedback is used to partition the picture into different level of grid and each grid data is treated as the input for the network. Multiple levels of gridding are applied corresponding to the layers of neural network. Samples are provided for training and verification and the result is satisfiable. The new method need is faster and can be used both in fish farm and waterway monitoring. Matlab programming is used for data processing.