Translation and rotation-invariant pattern recognition method using neural network with back-propagation
Yasuyuki Onodera, Hiroyuki Watanabe, Akira Taguchi, N. Iijima, M. Sone, Hideo Mitsui · 1992
The authors present a new translation and rotation invariant pattern recognition method using a neural network. It is clear that the left-right, up-down translation or/and rotation invariance are achieved by simple preprocessing of the original patterns without improvement of the network structure. They use a three layer feed-forward network with back-propagation for learning and recognition. The proposed method has the following merits: the net size is relative small, learning and recognition is easy. Moreover, a 100 percent recognition rate is realized by the proposed method, for the alphabet.>