Narrow Results

We present two methods of modelling ordered datasets using Baldwin's mass assignment. The first method generates a simplified memory-based fuzzy belief updating model. Results are given in application to particle classification and facial feature detection. The second method uses a new, high level, fuzzy trend feature based on a set of fuzzy trend prototypes. These prototypes are closely related to human perceptions of shape in ordered series. The models generated using this method are concise and linguistically clear glass box models. Results are given in application to sunspot and simple sinewave data series.

We present a soft computing approach to character recognition from printed documents. For feature extraction, we define a number of fuzzy sets on the Hough transform of character pattern pixels and synthesize additional fuzzy sets by t-norms. The height of each t-norm constitutes a feature element and a set of 'n' such feature elements form an n-dimensional feature vector for the character. A 3n-dimensional vector is then generated from the n-dimensional feature vector by defining three linguistic fuzzy sets, namely, weak, moderate and strong. These 3n-dimensional vectors form a Multilayer Perceptron (MLP) input for training by back propagation. The MLP outputs represent fuzzy sets denoting the belongingness of an input pattern to a number of fuzzy pattern classes. The feature set is chosen by optimizing a Feature Quality Index (FQI) using genetic algorithm. A two-state Markov chain is used to model degraded document images for simulation tests. The system can recognize characters with an accuracy of 98%.