Clustering by Principal Curve with Tree Structure

Data clustering is intensively used in signal processing in tasks such as multimedia compression, segmentation and pattern matching. In this work we extend the use of principal curves in clustering to complex multidimensional datasets. The use of principal curve in clustering is limited for high complexity data Automatic parameterization of the principal curve to assure good results for different datasets is a difficult task. We propose to use the tree structure to capture the general settlement of the data. Using this topology, regions of the dataset can be extracted individually clustered using the principal curve and then optimally recombined: The experiments show the improvement of the new method over the principal curve based clustering and the good performance compared to other clustering methods.