Interest in the automatic processing and analysis of document images has been rapidly increasing during the past few years. This book consists of 14 revised and expanded contributions that were originally presented at the IAPR workshop on Structural and Syntatic Pattern Recognition, held in Bern, Switzerland, in 1992. It addresses the different subfields of document image analysis, including preprocessing and segmentation, form processing, handwriting recognition, line drawing and map processing, and contextual processing.

Optical character recognition and document image analysis have become important areas with a fast-growing number of researchers in the field. This handbook with contributions by eminent experts, presents both the theoretical and practical aspects at an introductory level wherever possible.

Neural networks and fuzzy techniques are among the most promising approaches to pattern recognition. Neuro-fuzzy systems aim at combining the advantages of the two paradigms. This book is a collection of papers describing state-of-the-art work in this emerging field. It covers topics such as feature selection, classification, classifier training, and clustering. Also included are applications of neuro-fuzzy systems in speech recognition, land mine detection, medical image analysis, and autonomous vehicle control. The intended audience includes graduate students in computer science and related...

The field of pattern recognition has seen enormous progress since its beginnings almost 50 years ago. A large number of different approaches have been proposed. Hybrid methods aim at combining the advantages of different paradigms within a single system.

Hybrid Methods in Pattern Recognition is a collection of articles describing recent progress in this emerging field. It covers topics such as the combination of neural nets with fuzzy systems or hidden Markov models, neural networks for the processing of symbolic data structures, hybrid methods in data mining, the combination of symbolic...

Robotics is a highly interdisciplinary research topic, that requires integration of methods for mechanics, control engineering, signal processing, planning, gra- ics, human-computer interaction, real-time systems, applied mathematics, and software engineering to enable construction of fully operational systems. The diversity of topics needed to design, implement, and deploy such systems implies that it is almost impossible for individual teams to provide the needed critical mass for such endeavors. To facilitate interaction and progress on sensor-based intelligent robotics inter-disciplinary...