Data clustering has become one of the most important research areas of pattern recognition. The objective of data clustering is to use the cluster concept to simply the representation of large amount of data objects and generate meaningful clusters for further analysis and interpretation. Such a technology is useful in many disciplines, such as computational biology, bioinformatics, medical image processing, digital image segmentation, affective computing, real-time market forecast and online document clustering search engine. There are several crucial steps in a pattern analysis system based on data clustering methodologies. These include data collection, feature extraction/selection, clustering strategy, and clustering output interpretation. Among these issues, the clustering method is an especially important one. Robustness, efficiency, extendibility, and universality of a data clustering analysis system are usually determined by the data clustering method. However, there is no universal clustering technique that is always applicable for uncovering the variety of structures present in the data sets. This thesis focuses on the development of adaptive, robust, and generalized data clustering methods for real applications.