拡散連想型ニューラルネットによる顔の位置と形状認識

概要

論文の詳細を見る
Human being can recognize an object (e.g., face) position and shape at once by the parallel information processing systems (i.e., spatial and shape recognition systems) in the brain. The spatial and shape recognition systems depend primarily on parietal cortex (PG) and inferotemporal cortex (IT), respectively. The IT neurons responded to the shape of some objects (e.g., faces) rather selectively. On the contrary, PG neurons are related to spatial discrimination and spatial-to-motor coordinate transformation. In the present study, a spatial spreading associative neural network (SSAN net) that imitates the spatial recognition system in the brain is developed. The SSAN net achieves the shape-invariant positional and the position-invariant face shape recognition at once, similarly as human being recognizes the face position and shape.
社団法人電子情報通信学会の論文
1997-08-13