This book proposes a number of promising models and methods for adaptive segmentation, swarm partition, permissible segmentation, and transform properties, as well as techniques for spatio-temporal video segmentation and interpretation, online fuzzy clustering of data streams, and fuzzy systems for information retrieval. The main focus is on the spatio-temporal segmentation of visual information.
Sets of meaningful and manageable image or video parts, defined by visual interest or attention to higher-level semantic issues, are often vital to the efficient and effective processing and interpretation of viewable information. Developing robust methods for spatial and temporal partition represents a key challenge in computer vision and computational intelligence as a whole.
This book is intended for students and researchers in the fields of machine learning and artificial intelligence, especially those whose work involves image processing and recognition, video parsing, and content-based image/video retrieval.
