Multilevel Data Classification and Function Approximation Using Hierarchical Neural Networks

Combining diverse features and multiple classifiers is an open research area in which no optimal strategy is found but successful experimental studies have been performed depending on a specific task at hand. In this chapter, a strategy for combining diverse features and multiple classifiers is presented as an exemplary new model in multilevel data classification using hierarchical neural networks. In the proposed strategy, each feature set and each classifier extracts its own representation from the raw data which results with measurements extracted from the original data (or a subset of original data) that are unique to each level of approximation/classification. Later on, the results of each level are linearly combined in function approximation or merged in classification. It is shown by advanced signal and image processing applications that proposed model of combining features/classifiers is especially important for applications that require integration of different types of features and classifiers.