Recognition of objects normalized in log-polar space using Kohonen networks

In the paper, an algorithm is presented for the construction of representations of 18 object classes, which can be later recognized by a hybrid neural network. The preprocessing took place in log-polar space and it included: object centering, binarization, edge detection, normalization of angular position and scaling. After the normalization and log-Hough transformation, the maxima have been projected onto respective axes. In the paper, results have been discussed of neural network learning using such constructed representations, and the map of features for the Kohonen layer has been analyzed