TEXTBOOK (CSE 616)                                                                        

Required: Duda et al, Pattern Classification 2^nd Edition with Computer Manual 2nd Edition Set, Wiley, May 2004, ISBN 0-471-70350-8

"The first edition of this book, published 30 years ago by Duda and Hart, has been a defining book for the field of Pattern Recognition. Stork has done a superb job of updating the book. He has undertaken a monumental task of sifting through 30 years of material in a rapidly growing field and presented another snapshot of the field, determining what will be of importance for the next 30 years and incorporating it into this second edition. The style is easy to read as in the original book and the statistical, mathematical material comes alive with many new illustrations. The end result is harmonious, leading the reader through many new topics..." –Sargur N. Srihari, PhD, Director, Center for Excellence in Document Analysis and Recognition, Distinguished Professor, Department of Computer Science and Engineering, SUNY at Buffalo

Practitioners developing or investigating pattern recognition systems in such diverse application areas as speech recognition, optical character recognition, image processing, or signal analysis, often face the difficult task of having to decide among a bewildering array of available techniques. This unique text/professional reference provides the information you need to choose the most appropriate method for a given class of problems, presenting an in-depth, systematic account of the major topics in pattern recognition today. A new edition of a classic work that helped define the field for over a quarter century, this practical book updates and expands the original work, focusing on pattern classification and the immense progress it has experienced in recent years. Special features include:

• Clear explanations of both classical and new methods, including neural networks, stochastic methods, genetic algorithms, and theory of learning
• Over 350 high-quality, two-color illustrations highlighting various concepts
• Numerous worked examples
• Pseudocode for pattern recognition algorithms
• Expanded problems, keyed specifically to the text
• Complete exercises, linked to the text
• Algorithms to explain specific pattern-recognition and learning techniques
• Historical remarks and important references at the end of chapters
• Appendices covering the necessary mathematical background

 

David G. Stork, Elad Yom-Tov, Computer Manual in MATLAB to Accompany Pattern Classification, 2nd Edition, 2004

Pattern classification is a vital and growing field with applications in such areas as speech recognition, handwriting recognition, computer vision, image analysis, data mining, information retrieval, machine learning and neural networks. Computer Manual in MATLAB to accompany Pattern Classification, Second Edition, serves as both a companion to Pattern Classification, Second Edition, and as a professional software toolbox for researchers in pattern classification and signal processing.

Beginning with an introduction to programming in MATLAB suitable for readers with no such programming experience, this Manual and its accompanying software:

• Implement all the algorithms described in Pattern Classification, Second Edition
• Implement important recent algorithms not found in the text
• Use the same terminology as the text
• Include representative data sets, including those from the computer exercises in the text
• Include step-by-step worked examples, including some of the examples and figures in the text
• Provide self-annotated code so the user can easily navigate, understand, and modify the code