Experimenting Multiresolution Analysis for Identifying Regions of Different Classification Complexity

Systems for assessing the classification complexity of a dataset have received increasing attention in research activities on pattern recognition. These systems typically aim at quantifying the overall complexity of a domain, with the goal of comparing different datasets. In this work, we propose a method for partitioning a dataset into regions of different classification complexity, so to highlight sources of complexity inside the dataset. Experiments have been carried out on relevant datasets, proving the effectiveness of the proposed method.