Pattern Recognition

Sergios Theodoridis, Konstantinos Koutroumbas

690 pages, parution le 16/06/2003 (2^eme édition)

Ajouter à une liste

Indisponible

Résumé

Pattern recognition is incredibly important in all automation, information handling and retrieval applications. The new edition of Pattern Recognition, a text written by two of the field's leading experts, covers the entire spectrum of pattern recognition applications from an engineering perspective, examining topics from image analysis to speech recognition and communications. This thoroughly updated edition presents cutting-edge material on neural networks and highlights the latest developments in this growing field, including independent components and support vector machines. Developed through more than 10 years of teaching experience, Pattern Recognition is the most comprehensive reference available for both engineering students and practicing engineers.

Coverage Includes:

Latest techniques in feature generation, including features based onWavelets, Wavelet Packets, Fractals and a new section on Independent Component Analysis (ICA)
All new sections on Support Vector Machines, Deformable Template Matching and a related appendix on Constrained Optimization
Feature selection techniques
Design of linear and non-linear classifiers, including Bayesian, Multilayer Perceptrons, Decision Trees and RBF networks
Context-dependent classification, including Dynamic Programming and Hidden Markov Modeling techniques
Classical approaches, as well as the most recent developments in clustering algorithms, such as fuzzy, possibilistic, morphological, genetic, and annealing techniques
Coverage of numerous, diverse applications, including Image Analysis, Character Recognition, Medical Diagnosis, Speech Recognition, and Channel Equalization
Numerous computer simulation examples, supporting the methods given in the book, available via the Web

Introduction
Classifiers Based on Bayes Decision Theory
Support Vector machines (linear case)
Support Vector Machines (nonlinear case)
Decision trees
Linear Classifiers
Non Linear Classifiers
Deformable Template Matching
Feature Selection
Feature Generation I: Linear Transforms
Feature Generation II. Template Matching
Context Dependent Classification
System Evaluation Clustering: Basic Concepts
Clustering Algorithms I: Sequential Algorithms
Clustering Algorithms II: Hierarchical Algorithms
Clustering Algorithms III: Schemes Based on Function Optimization
Clustering Algorithms IV. Cluster Validity
Appendices

Caractéristiques techniques

	PAPIER
Éditeur(s)	Academic Press
Auteur(s)	Sergios Theodoridis, Konstantinos Koutroumbas
Parution	16/06/2003
Édition	2^eme édition
Nb. de pages	690
Format	16 x 23,5
Couverture	Broché
Poids	1050g
Intérieur	Noir et Blanc
EAN13	9780126858754
ISBN13	978-0-12-685875-4