Recognition and segmentation of facial components using selective attention mechanism
Hideki Hashimoto, Kunihiko Fukushima · Systems and Computers in Japan · 1999
A network is proposed to recognize and extract the face as well as eyes and mouth from an image with complex background. The proposed network is an improved model of the selective attention mechanism based on interaction between two processing systems with different resolutions. The network's performance was evaluated by learning of several frontal facial images of nearly the same size. Even with such sparse learning, the proposed network proved to be quite efficient in recognition and extraction of test images that offered a variety of face patterns. © 1999 Scripta Technica, Syst Comp Jpn, 30(9): 55–63, 1999