Proposal of an automatic fish sorting system by intelligent image processing

In this research, we have proposed a fish sorting system to aim at automatic sorting. It is constructed with a conveyance part, a capturing image part and a recognition part, respectively. Especially, we have adopted a flexible sorting system using neural network (NN) in the recognition part. We have developed an independent conveyance system. The independent conveyance system can convey one piece of fish from several intertwined fishes. We adopt two-dimensional fast Fourier transform (2DFFT) for generating input of the NN. We suppose the converted data by the 2DFFT is invariable to the rotation of the fish. In this paper, we examine the recognition capability and conveyance capability.