2016 年 82 巻 835 号 p. 15-00518
Up to now, we discuss a non-linear recognition system for the carved seal of the steal, which has several problems for the image processing and recognition for this research theme such as reflection, roundness, whole carved seal image and partial one. Sometimes these cause miss-recognition for the carved seal. We newly adopt the neural network to this carved seal recognition. This NN has radial based function as an output function for the localization of the recognition range. We discuss the recognition ability according to the several conditions such as lighting and editing method of the learning data for the NN using image of the steal ball for the pinball game. First, we analyze them from a viewpoint of the advanced image processing and construct the neuro recognition system for the carved seal. Finally, we show its effectiveness and feasibility by the simulation with image of the carved seal of the pinball.
