Neural networks and Hough transform for pattern recognition

The Hough transform (HT) is a very efficient technique in pattern recognition for performing template matching of curves and is very suitable for implementation in parallel hardware. The paper presents the HT as a neural network (NN). This fact suggests that the HT can be used to determine the parameters of the 'neurons' responsible for the detection of patterns to be recognized. After a brief review of the relevant aspects of the HT, the authors describe how the HT is related to NNs and propose a very efficient real time NN digital system for recognition of patterns built up of line-segments. A complete example has also been included.