Detection and normalization of pattern position by neural network

摘要

The authors propose a method of detecting and normalizing patternposition by the backpropagation network (BN) with three layers. First,they clarify the troublesome situation of restoring the shifted positionby BPN experimentally, using a one-dimensional signal. Next, it is shownthat by cascading two networks, one can detect and normalize the signalposition and demonstrate its usefulness. This method is applied to atwo-dimensional image, and its validity is confirmed