Title :
Rotation-invariant neural pattern recognition system with application to coin recognition
Author :
Fukumi, Minoru ; Omatu, Sigeru ; Takeda, Fumiaki ; Kosaka, Toshihisa
Author_Institution :
Fac. of Eng., Tokushima Univ., Japan
fDate :
3/1/1992 12:00:00 AM
Abstract :
In pattern recognition, it is often necessary to deal with problems to classify a transformed pattern. A neural pattern recognition system which is insensitive to rotation of input pattern by various degrees is proposed. The system consists of a fixed invariance network with many slabs and a trainable multilayered network. The system was used in a rotation-invariant coin recognition problem to distinguish between a 500 yen coin and a 500 won coin. The results show that the approach works well for variable rotation pattern recognition
Keywords :
computerised pattern recognition; neural nets; 500 won coin; 500 yen coin; coin recognition; computerised pattern recognition; fixed invariance network; rotation-invariant neural pattern recognition system; trainable multilayered network; Associate members; Data preprocessing; Explosions; Fourier transforms; Neural networks; Neurons; Pattern matching; Pattern recognition; Resonance; Slabs;
Journal_Title :
Neural Networks, IEEE Transactions on
