Preface background in statistics and mathematics, with the necessary additional material integrated into the text so that the book is essentially self-contained. The book is suitable both for individual study and for classroom use for students physics, computer science, computer engineering, electronic engineering medical engineering, and applied mathematics taking senior undergraduate and graduate courses in pattern recognition and machine learning. It presents a compre hensive introduction to the core concepts that must be understood in order to make independent contributions to the field. It is designed to be accessible to newcomers rom varied backgrounds, but it will also be useful to researchers and professionals n image and signal processing and analysis, and in computer vision. The goal is to present the fundamental concepts of supervised and unsupervised classification in an informal, rather than axiomatic, treatment so that the reader can quickly acquire the necessary background for applying the concepts to real problems. A final chapter indicates some useful and accessible projects which may be undertaken WeuseiMagej(http://rsbweb.nihgov/ij/)andtherelateddistributionFiji(http:// fiji. sc/wiki/index. php/ Fiji) in the early stages of image exploration and analysis, because of its intuitive interface and ease of use. We then tend to move on to MATLAB for its extensive capabilities in manipulating matrices and its image processing and statistics toolboxes. We recommend using an attractive GUI called Diplmage(fromhttp://www.diplib.org/download)toavoidmuchofthecommand line typing when manipulating images. There are also classification toolboxes availableforMatlab,suchasClassificationToolbox(http://www.wiley.com/ Wiley CDA/Section/id-105036. html) which requires a password obtainable from theassociatedcomputermanual)andPrtoOls(hTtp://www.prtools.org/download html). We use the Classification Toolbox in Chap. 8 and recommend it highly for its intuitive GUl. Some of our students have explored Weka, a collection of machine learning algorithms for solving data mining problems implemented in Java and open sourced(http://www.cs.waikatoac.nz/ml/weka/index_downloading.html There are a number of additional resources which can be downloaded from the companionWebsiteforthisbookathttp://extras.springercom/,includingseveral Useful Excel files and data files. Lecturers who adopt the book can also obtain access to the end-of-chapter exercises In spite of our best efforts at proofreading, it is still possible that some typos ma have survived. Please notify me if you find any I have very much enjoyed writing this book; I hope you enjoy reading it Camarillo. cabackground in statistics and mathematics, with the necessary additional material integrated into the text so that the book is essentially self-contained. The book is suitable both for individual study and for classroom use for students in physics, computer science, computer engineering, electronic engineering, bio￾medical engineering, and applied mathematics taking senior undergraduate and graduate courses in pattern recognition and machine learning. It presents a compre￾hensive introduction to the core concepts that must be understood in order to make independent contributions to the field. It is designed to be accessible to newcomers from varied backgrounds, but it will also be useful to researchers and professionals in image and signal processing and analysis, and in computer vision. The goal is to present the fundamental concepts of supervised and unsupervised classification in an informal, rather than axiomatic, treatment so that the reader can quickly acquire the necessary background for applying the concepts to real problems. A final chapter indicates some useful and accessible projects which may be undertaken. We use ImageJ (http://rsbweb.nih.gov/ij/) and the related distribution, Fiji (http:// fiji.sc/wiki/index.php/Fiji) in the early stages of image exploration and analysis, because of its intuitive interface and ease of use. We then tend to move on to MATLAB for its extensive capabilities in manipulating matrices and its image processing and statistics toolboxes. We recommend using an attractive GUI called DipImage (from http://www.diplib.org/download) to avoid much of the command line typing when manipulating images. There are also classification toolboxes available for MATLAB, such as Classification Toolbox (http://www.wiley.com/ WileyCDA/Section/id-105036.html) which requires a password obtainable from the associated computer manual) and PRTools (http://www.prtools.org/download. html). We use the Classification Toolbox in Chap. 8 and recommend it highly for its intuitive GUI. Some of our students have explored Weka, a collection of machine learning algorithms for solving data mining problems implemented in Java and open sourced (http://www.cs.waikato.ac.nz/ml/weka/index_downloading.html). There are a number of additional resources, which can be downloaded from the companion Web site for this book at http://extras.springer.com/, including several useful Excel files and data files. Lecturers who adopt the book can also obtain access to the end-of-chapter exercises. In spite of our best efforts at proofreading, it is still possible that some typos may have survived. Please notify me if you find any. I have very much enjoyed writing this book; I hope you enjoy reading it! Camarillo, CA Geoff Dougherty vi Preface