Title :
Shape, orientation and size recognition of normal and ambiguous faces by a rotation and size spreading associative neural network
Author :
Nakamura, Kiyomi ; Arimura, Kazuya ; Takase, Kazuya
Author_Institution :
Graduate Sch. of Eng., Toyama Prefectural Univ., Japan
fDate :
6/24/1905 12:00:00 AM
Abstract :
In the present study, we developed a rotation and size spreading associative neural network (RS-SAN net) to accomplish view invariant recognition of human faces. Then we developed an extended RS-SAN net to accomplish view dependent recognition of ambiguous faces. The RS-SAN net correctly recognized face shape irrespective of its orientation and size, the face orientation irrespective of its shape and size, and the face size irrespective of its shape and orientation. The extended RS-SAN net recognizes each ambiguous face as two different faces depending on whether it is upright or inverted, irrespective of its size
Keywords :
content-addressable storage; face recognition; neural nets; RS-SAN net; ambiguous faces; face orientation recognition; face shape recognition; face size recognition; rotation associative neural network; size spreading associative neural network; view invariant recognition; Artificial neural networks; Biological neural networks; Face recognition; Humans; Neurons; Object recognition; Psychology; Retina; Shape; Storage area networks;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1007524
