Fuzzy Models And Algorithms For Pattern Recognition And Image Processing

by Bezdek, James C.; Keller, James; Krisnapuram, Raghu; Pal, Nikhil R.

• ISBN13: 9780387245157
• ISBN10: 0387245154
• Format: Paperback
• Copyright: 2005-03-25
• Publisher: Springer Verlag

Summary

Fuzzy Models and Algorithms for Pattern Recognition and Image Processing presents a comprehensive introduction of the use of fuzzy models in pattern recognition and selected topics in image processing and computer vision. Unique to this volume in the Kluwer Handbooks of Fuzzy Sets Series is the fact that this book was written in its entirety by its four authors. A single notation, presentation style, and purpose are used throughout. The result is an extensive unified treatment of many fuzzy models for pattern recognition. The main topics are clustering and classifier design, with extensive material on feature analysis relational clustering, image processing and computer vision. Also included are numerous figures, images and numerical examples that illustrate the use of various models involving applications in medicine, character and word recognition, remote sensing, military image analysis, and industrial engineering.

Table of Contents

Series Foreword	v
Preface	vii
Pattern Recognition	1	(10)
Fuzzy models for pattern recognition	1	(6)
Why fuzzy pattern recognition?	7	(1)
Overview of the volume	8	(2)
Comments and bibliography	10	(1)
Cluster Analysis for Object Data	11	(126)
Cluster analysis	11	(3)
Batch point-prototype clustering models	14	(25)
The c-means models	16	(7)
Semi-supervised clustering models	23	(6)
Probabilistic Clustering	29	(5)
Remarks on HCM/FCM/PCM	34	(3)
The Reformulation Theorem	37	(2)
Non point-prototype clustering models	39	(48)
The Gustafson-Kessel (GK) Model	41	(4)
Linear manifolds as prototypes	45	(7)
Spherical Prototypes	52	(2)
Elliptical Prototypes	54	(2)
Quadric Prototypes	56	(8)
Norm induced shell prototypes	64	(5)
Regression models as prototypes	69	(6)
Clustering for robust parametric estimation	75	(12)
Cluster Validity	87	(34)
Direct Measures	90	(1)
Davies-Bouldin Index	90	(2)
Dunn's Index	92	(4)
Indirect measures for fuzzy clusters	96	(9)
Standardizing and normalizing indirect indices	105	(4)
Indirect measures for non-point prototype models	109	(8)
Fuzzification of statistical indices	117	(4)
Feature Analysis	121	(9)
Comments and bibliography	130	(7)
Cluster Analysis for Relational Data	137	(46)
Relational Data	137	(9)
Crisp Relations	138	(5)
Fuzzy Relations	143	(3)
Object Data to Relational Data	146	(3)
Hierarchical Methods	149	(4)
Clustering by decomposition of fuzzy relations	153	(5)
Relational clustering with objective functions	158	(20)
The Fuzzy Non Metric (FNM) model	159	(1)
The Assignment-Prototype (AP) Model	160	(5)
The relational fuzzy c-means (RFCM) model	165	(3)
The non-Euclidean RFCM (NERFCM) model	168	(10)
Cluster validity for relational models	178	(2)
Comments and bibliography	180	(3)
Classifier Design	183	(364)
Classifier design for object data	183	(7)
Prototype classifiers	190	(11)
The nearest prototype classifier	190	(6)
Multiple prototype designs	196	(5)
Methods of prototype generation	201	(40)
Competitive learning networks	203	(4)
Prototype relabeling	207	(1)
Sequential hard c-means (SHCM)	208	(1)
Learning vector quantization (LVQ)	209	(2)
Some soft versions of LVQ	211	(1)
Case Study: LVQ and GLVQ-F 1-nmp designs	212	(7)
The soft competition scheme (SCS)	219	(3)
Fuzzy learning vector quantization (FLVQ)	222	(8)
The relationship between c-Means and CL schemes	230	(2)
The mountain ``clustering'' method (MCM)	232	(9)
Nearest neighbor classifiers	241	(12)
The Fuzzy Integral	253	(15)
Fuzzy Rule-Based Classifiers	268	(102)
Crisp decision trees	269	(4)
Rules from crisp decision trees	273	(5)
Crisp decision tree design	278	(10)
Fuzzy system models and function approximation	288	(15)
The Chang - Pavlidis fuzzy decision tree	303	(5)
Fuzzy relatives of ID3	308	(17)
Rule-based approximation based on clustering	325	(34)
Heuristic rule extraction	359	(9)
Generation of fuzzy labels for training data	368	(2)
Neural-like architectures for classifications	370	(43)
Biological and mathematical neuron models	372	(6)
Neural network models	378	(15)
Fuzzy Neurons	393	(10)
Fuzzy aggregation networks	403	(7)
Rule extraction with fuzzy aggregation networks	410	(3)
Adaptive resonance models	413	(29)
The ART1 algorithm	414	(7)
Fuzzy relatives of ART	421	(4)
Radial basis function networks	425	(17)
Fusion techniques	442	(49)
Data level fusion	443	(10)
Feature level fusion	453	(1)
Classifier fusion	454	(37)
Syntactic pattern recognition	491	(32)
Language-based methods	493	(14)
Relation-based methods	507	(16)
Comments and bibliography	523	(24)
Image Processing and Computer Vision	547	(134)
Introduction	547	(3)
Image Enhancement	550	(12)
Edge Detection and Edge Enhancement	562	(10)
Edge Linking	572	(7)
Segmentation	579	(22)
Segmentation via thresholding	580	(2)
Segmentation via clustering	582	(6)
Supervised segmentation	588	(4)
Rule-Based Segmentation	592	(9)
Boundary Description and Surface Approximation	601	(23)
Linear Boundaries and Surfaces	603	(8)
Circular Boundaries	611	(4)
Quadric Boundaries/Surfaces	615	(6)
Quadric surface approximation in range images	621	(3)
Representation of Image Objects as Fuzzy Regions	624	(15)
Fuzzy Geometry and Properties of Fuzzy Regions	625	(5)
Geometric properties of original and blurred objects	630	(9)
Spatial Relations	639	(12)
Perceptual Grouping	651	(7)
High-Level Vision	658	(5)
Comments and bibliography	663	(18)
References cited in the text	681	(62)
References not cited in the text	743	(10)
Appendix 1 Acronyms and abbreviations	753	(6)
Appendix 2 The Iris Data: Table I, Fisher (1936)	759