Classification of invariant image representations using a neural network

A neural network (NN) based approach for classification of images represented by translation-, scale-, and rotation-invariant features is presented. The utilized network is a multilayer perceptron (MLP) classifier with one hidden layer. Back-propagation learning is used for its training. Two types of features are used: moment invariants derived from geometrical moments of the image, and features based on Zernlike moments, which are the mapping of the image onto a set of complex orthogonal polynomials. The performance of the MLP is compared to the Bayes, nearest-neighbor, and minimum-mean-distance statistical classifiers. Through extensive experimentation with noiseless as well as noisy binary images of all English characters (26 classes), the following conclusions are reached: (1) the MLP outperforms the other three classifiers, especially when noise is present; (2) the nearest-neighbor classifier performs about the same as the NN for the noiseless case; (3) the NN can do well even with a very small number of training samples; (4) the NN has a good degree of fault tolerance; and (5) the Zernlike-moment-based features possess strong class separability power and are more powerful than moment invariants