Rotation invariant neural pattern recognition system which can estimate a rotation angle

This paper presents a rotation invariant neural pattern recognition system, which can recognize a rotated pattern and estimate a rotation angle. The system is very effective for a rotated coin recognition problem, but is poor compared with human performance. It is well known that human sometimes recognizes a rotated pattern by means of the mental rotation. Such a fact, however, has never been considered and used in neural pattern recognition systems, especially in rotation invariant systems. Therefore, we examine the principle of mental rotation and apply it to a rotation invariant pattern recognition system. The system with such a principle could recognize a rotated pattern and estimate a rotation angle. It is shown that the system is effective to recognize a rotated pattern from results of computer simulation for a coin recognition problem.<<ETX>>

[1]  R. Shepard,et al.  Mental Rotation of Three-Dimensional Objects , 1971, Science.

[2]  Takayuki Ito,et al.  Neocognitron: A neural network model for a mechanism of visual pattern recognition , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[3]  Bernard Widrow,et al.  Layered neural nets for pattern recognition , 1988, IEEE Trans. Acoust. Speech Signal Process..

[4]  Minoru Fukumi,et al.  A new back-propagation algorithm with coupled neuron , 1991, International 1989 Joint Conference on Neural Networks.

[5]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[6]  Y. Takano Perception of rotated forms: A theory of information types , 1989, Cognitive Psychology.

[7]  Minoru Fukumi,et al.  A new neuron model "cone" with fast convergence rate and its application to pattern recognition , 1991, Systems and Computers in Japan.

[8]  Noboru Ohnishi,et al.  Augmented multi-layer perceptron for rotation- and scale-invariant hand-written numeral recognition , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[9]  Christopher Ting,et al.  Rotation invariant neocognitron , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[10]  Hideki Asoh,et al.  A Neural Network for Learning and Recognizing Rotated Patterns , 1991 .

[11]  Sigeru Omatu,et al.  Rotation Invariant Neural Network with An Edge Detection Network , 1992 .

[12]  Minoru Fukumi,et al.  Rotation-invariant neural pattern recognition system with application to coin recognition , 1992, IEEE Trans. Neural Networks.

[13]  Sigeru Omatu,et al.  Neural Pattern Recognition System Invariant to Rotation of Input Pattern and Its Application to Coin Recognition , 1992 .

[14]  F. Takeda,et al.  Bank note recognition system Using Neural network with random masks , 1993 .

[15]  Minoru Fukumi,et al.  Designing a neural network for coin recognition by a genetic algorithm , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[16]  G. E. Ford,et al.  Network model for invariant object recognition and rotation angle estimation , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).