Pattern Recognition and Image Analysis

0.0

Pattern recognition is at the heart of applications ranging from the identification of white blood cells to the selection of tax returns for auditing, from earthquake prediction to speech recognition. This book is an ideal introduction to pattern recognition for both higher-level undergraduate and beginning graduate courses. The text provides extensive worked examples and realistic applications that have been thoroughly classroom-tested. Since images are often the input to pattern recognition systems, a survey of image processing theory is included, covering techniques such as scene segmentation, Hough transforms, least squares, eigenvector line fitting, and Fourier transforms. The following important aspects of pattern recognition are also presented. Key Features Probability theory Statistical decision making, including Bayes' Theorem Nonparametric decision making, including histograms Hierarchical and partitional clustering: the advantages and risks Artificial neural networks_and how they work in real applications, such as classifying sex from facial images. Readers do not need computer science expertise or a mathematics background beyond elementary calculus. The book includes a disk with sample digital images and data files, a sample project with input file, SAS programs, and C program implementations of several major algorithms that are presented in the book. Table of Contents Preface Introduction Probability Statistical Decision Making Nonparametric Decision Making Clustering Artificial Neural Networks Processing of Waveforms and Images Image Analysis Appendices References Index