An image recognition based on neural oscillator network
Kenta Hoshino, Hajime Igarashi · 2010
This paper introduces a novel image recognition method based on the neural oscillator network. In the present method, the dynamics of neurons is determined from neural coupling strengths relevant to the similarities in pixel levels, which have been used in the conventional image segmentation, as well as geometrical local features obtained from the Gabor filtering. Then the image regions under resultant neural synchronization are identified. It is shown that the accuracy of the present method, applied to the image recognition for pairs of identical and different alphabetical letters, is 76.9% and 62.2%, respectively. Moreover, the simple polygons are also correctly recognized by the present method.