Statistical Pattern Recognition (Second Edition)

Author: Webb
Publisher:
Publish Date: 2004-10-01
Features: This book is concise and clear in its exposition, with well-defined concepts. The application examples are extensive and highly inspirational, making it an important reference for those engaged in pattern recognition research and application. It can also serve as a textbook for graduate-level courses in information-related fields. The book provides a comprehensive and detailed introduction to the fundamental theories and techniques of statistical pattern recognition. It includes important methods for classifier design and key techniques for data analysis and preprocessing. The former encompasses parametric and non-parametric methods based on probability density function estimation, as well as linear models, radial basis function networks, support vector machines, projection methods (neural networks), and discriminant analysis decision trees constructed from discriminant functions. The latter involves feature selection and feature extraction, as well as clustering analysis. Additionally, the book thoroughly discusses the evaluation of classifier characteristics and the improvement of classifier performance using ensemble techniques. Furthermore, it explores topics such as model selection, unreliable classification, missing data, outlier detection, and the mixture of continuous and discrete variables.