In computer vision, the interpretation of optical flow (motion vector field calculated from images) and estimation of motion are important tasks. This study proposes a motion interpretation network which enables optical flow (OF) interpretation and describes motions on a plane through the use of a neural network with complex back propagation learning. Furthermore, an OF normalization network for optical flow normalization is proposed for the interpretation of diverse flow patterns, such as real image optical flow. Two types of output function of a neuron unit are examined. Using test patterns and real image optical flow, the generalization capacity of proposed network is investigated. And the ability is confirmed experimentally.