Kanal / Gelsema Pattern Recognition and Artificial Intelligence, Towards an Integration

Proceedings of an International Workshop held in Amsterdam, May 18-20, 1988
1. Auflage 2014
ISBN: 978-1-4832-9945-7
Verlag: Elsevier Science & Techn.
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, Band Volume 7, 510 Seiten, Web PDF

Reihe: Machine Intelligence and Pattern Recognition

This volume brings together the results of research into the methodology and applications of pattern recognition, with particular emphasis given to the incorporation of artificial intelligence methodologies into pattern recognition systems.The first part of this volume covers image analysis and processing software, systems and algorithms. Pattern analysis and classifier design are dealt with in part two, while the last part deals with model based and expert systems, including uncertainty calculus methods in pattern analysis and object recognition. A number of specific application areas are considered, including such diverse topics as fingerprinting, astronomy, molecular biology and pathology.

Autoren/Hrsg.

Kanal, L. N.

Gelsema, E. S.

Inhaltsverzeichnis

1;Front Cover;1
2;Pattern Recognition and Artificial Intelligence: Towards an Integration;4
3;Copyright Page;5
4;Table of Contents;14
5;PREFACE;6
6;ACKNOWLEDGEMENTS;12
7;PART I: IMAGE PROCESSING;18
7.1;SECTION I: SYSTEMS;20
7.1.1;CHAPTER 1. ACUITY: IMAGE ANALYSIS FOR THE PERSONAL COMPUTER;22
7.1.1.1;1. Introduction;22
7.1.1.2;2. Using Acuity;24
7.1.1.3;3. Preparing an Experiment;24
7.1.1.4;4. Examining the Resulting Data;30
7.1.1.5;5. Exporting Data from an Experiment;31
7.1.1.6;6. Summary;32
7.1.1.7;References;32
7.1.2;CHAPTER 2. LILY: A SOFTWARE PACKAGE FOR IMAGE PROCESSING;34
7.1.2.1;1. INTRODUCTION;34
7.1.2.2;2. PROGRAMMING LANGUAGE CHOICE AND IT'S CONSEQUENCES;35
7.1.2.3;3. STRUCTURE OF THE PACKAGE;35
7.1.2.4;4. DATA REPRESENTATION, STRUCTURES AND SYNTAX;38
7.1.2.5;5. DOCUMENTATION;42
7.1.2.6;6. MAINTENANCE AND DEVELOPMENT TOOLS;44
7.1.2.7;7. IMAGE PROCESSING APPLICATIONS;44
7.1.2.8;8. CONCLUSION;48
7.1.2.9;REFERENCES;50
7.1.3;CHAPTER 3. REAL TIME PROCESSING OF IMAGES;52
7.1.3.1;1. INTRODUCTION;52
7.1.3.2;2. DIFFERENT REAL-TIME REQUIREMENTS;52
7.1.3.3;3. SYSTEMS WITH OPTIMAL RESPONSE-TIME;53
7.1.3.4;4. SYSTEMS WITH OPTIMAL THROUGHPUT;57
7.1.3.5;5. CONCLUSION;58
7.1.3.6;REFERENCES;58
7.1.4;DISCUSSIONS PART I , SECTION I;60
7.2;SECTION II: ALGORITHMS;64
7.2.1;CHAPTER 4. A NEW PROCEDURE FOR LINE ENHANCEMENT APPLIED TO FINGERPRINTS;66
7.2.1.1;1. ROTATION–INVARIANT OPERATORS;66
7.2.1.2;2. LINE DETECTION;69
7.2.1.3;3. THE FINGERPRINT APPLICATION;75
7.2.1.4;CONCLUSIONS;77
7.2.1.5;REFERENCES;77
7.2.2;CHAPTER 5. AN EDGE DETECTION MODEL BASED ON NON-LINEAR LAPLACEFILTERING;80
7.2.2.1;1. INTRODUCTION;80
7.2.2.2;2. EDGE DETECTION SCHEME;81
7.2.2.3;3. EVALUATION PROCEDURE;85
7.2.2.4;4. EXPERIMENTAL RESULTS;86
7.2.2.5;5. COMPARISONS;88
7.2.2.6;6. CONCLUSIONS;88
7.2.2.7;ACKNOWLEDGEMENT;89
7.2.2.8;REFERENCES;90
7.2.3;CHAPTER 6. PATTERN RECOGNITION BY DETECTION OF LOCAL SYMMETRIES;92
7.2.3.1;1 INTRODUCTION;92
7.2.3.2;2 MODELING THE LOCAL NEIGHBOURHOODS BY HARMONIC FUNCTIONS;93
7.2.3.3;3 DETECTION OF LOCAL SYMMETRIES;98
7.2.3.4;4 APPLICATIONS AND EXPERIMENTS;99
7.2.3.5;5 CONCLUSION;106
7.2.3.6;ACKNOWLEDGEMENTS;106
7.2.3.7;REFERENCES;107
7.2.4;CHAPTER 7. ACCURATE MEASUREMENT OF SHAPE AT LOW RESOLUTION;108
7.2.4.1;1. INTRODUCTION;108
7.2.4.2;2. THE METHOD FOR HIGH ACCURACY;111
7.2.4.3;3. CONCLUSION;118
7.2.4.4;ACKNOWLEDGEMENT;118
7.2.4.5;FOOTNOTES AND REFERENCES;118
7.2.5;CHAPTER 8. COMPUTING VISIBILITY PROPERTIES OF POLYGONS;120
7.2.5.1;Abstract;120
7.2.5.2;1. INTRODUCTION;120
7.2.5.3;2. VISIBILITY FROM A POINT;120
7.2.5.4;3. VISIBILITY FROM AN EDGE;121
7.2.5.5;4. DETERMINING THE VISIBILITY REGION FROM AN EDGE;123
7.2.5.6;5. DETECTING THE VISIBILITY OF A POLYGON FROM AN EDGE;126
7.2.5.7;6. DETECTING VISIBILITY BETWEEN TWO EDGES OF A POLYGON;129
7.2.5.8;REFERENCES;136
7.2.6;CHAPTER 9. USING VANISHING POINTS TO LOCATE OBJECTS WITH SIX DEGREES OF FREEDOM;140
7.2.6.1;1. INTRODUCTION;140
7.2.6.2;2. THE PROBLEM STATEMENT;143
7.2.6.3;3. SOLUTION USING VANISHING POINTS;145
7.2.6.4;4. ERROR ANALYSIS;148
7.2.6.5;5. PRELIMINARY EXPERIMENTAL RESULTS;152
7.2.6.6;6. CONCLUSION;156
7.2.6.7;ACKNOWLEDGMENTS;156
7.2.6.8;REFERENCES;156
7.2.7;CHAPTER 10. GRAPH CONSTRUCTION AND MATCHING FOR 3D OBJECT RECOGNITION;158
7.2.7.1;1. INTRODUCTION;158
7.2.7.2;2. PASSIVE APPROACH;159
7.2.7.3;3. OVERVIEW OF IMPLEMENTATION;159
7.2.7.4;4. 2D GRAPH BUILDING;160
7.2.7.5;5. PRIMITIVE MATCHING AND 3D TRANSFORMS;162
7.2.7.6;6. CONCLUSIONS;170
7.2.7.7;REFERENCES;171
7.2.8;CHAPTER 11. THREE–DIMENSIONAL RECONSTRUCTION OF MYOCARDIAL CONTRAST PERFUSION FROM BIPLANE CINEANGIOGRAMS.;172
7.2.8.1;1. INTRODUCTION;172
7.2.8.2;2. THREE-DIMENSIONAL RECONSTRUCTION BY MEANS OF LINEAR PROGRAMMING TECHNIQUES;173
7.2.8.3;3. DETERMINATION OF THE OPTIMAL BIPLANE ANGIOGRAPHIC VIEWS;174
7.2.8.4;4. MYOCARDIAL PERFUSION IMAGE ACQUISITION;175
7.2.8.5;5. DIGITIZATION AND PREPROCESSING OF THE SELECTED IMAGES;175
7.2.8.6;6. RECONSTRUCTION OF GEOMETRY;176
7.2.8.7;7. RECONSTRUCTION OF REGIONAL MYOCARDIAL PERFUSION;179
7.2.8.8;8. FIRST EXPERIMENTAL RESULTS;181
7.2.8.9;9. CONCLUSIONS;183
7.2.8.10;ACKNOWLEDGEMENTS;184
7.2.8.11;REFERENCES;184
7.2.9;CHAPTER 12. AUTOMATED CENTERLINE TRACING IN CORONARY ANGIOGRAMS;186
7.2.9.1;1. INTRODUCTION;186
7.2.9.2;2. METHODOLOGY;188
7.2.9.3;3. POSTPROCESSING;191
7.2.9.4;4. VALIDATION PROCEDURE;192
7.2.9.5;5. RESULTS;194
7.2.9.6;6. REPRODUCIBILITY;196
7.2.9.7;7. DISCUSSION;198
7.2.9.8;ACKNOWLEDGEMENTS;199
7.2.9.9;REFERENCES;199
7.2.10;CHAPTER 13. SHAPE ESTIMATION IN COMPUTER TOMOGRAPHY FROM MINIMALDATA;202
7.2.10.1;1. INTRODUCTION;202
7.2.10.2;2. THEORY;203
7.2.10.3;3. ERROR ANALYSIS FOR AREA ESTIMATIONS;209
7.2.10.4;4. EXPERIMENTAL RESULTS;210
7.2.10.5;5. CONCLUSION;214
7.2.10.6;ACKNOWLEDGEMENT;217
7.2.10.7;REFERENCES AND NOTES;217
7.2.11;DISCUSSIONS PART I, SECTION II;218
8;PART II: PATTERN RECOGNITION;226
8.1;Chapter 14. Classifier Design with Parzen Windows;228
8.1.1;1. INTRODUCTION;228
8.1.2;2. CLASSIFIER DESIGN IN PRACTICE;229
8.1.3;3. PARZEN WINDOW DENSITY ESTIMATES;232
8.1.4;4. PERFORMANCE OF CLASSIFIERS ON REAL DATA SETS;240
8.1.5;5. CONCLUSIONS;241
8.1.6;6. REFERENCES;244
8.2;CHAPTER 15. DISCRIMINANT ANALYSIS IN A NON-PROBABILISTIC CONTEXTBASED ON FUZZY LABELS;246
8.2.1;1. Problem definition;246
8.2.2;2. The choice of the error criterion;247
8.2.3;3. Classification and error estimation;248
8.2.4;4. Class separation and feature selection;250
8.2.5;5. Discussion;250
8.2.6;6. Conclusion and summary;251
8.2.7;7. References;251
8.3;CHAPTER 16. INCOMPLETE DATA SETS;254
8.3.1;1. Introduction;254
8.3.2;2. Classification of an object with missing values;255
8.3.3;3. Design of a classifier using an incomplete data set;256
8.3.4;4. Estimation of missing values;258
8.3.5;5. Experiments;261
8.3.6;6. Final remarks;270
8.3.7;REFERENCES;271
8.4;CHAPTER 17. A Structural Look at Pattern Recognition From the Point of View of Rate-Distortion Theory;274
8.4.1;ABSTRACT;274
8.4.2;1.0 Introduction;274
8.4.3;2.0 Rate - Distortion Theory;275
8.4.4;3.0 Modeling of the Pattern Recognition Process;279
8.4.5;4.0 Two-Class Pattern Recognition;281
8.4.6;5.0 Correlated Patterns;288
8.4.7;6.0 Conclusions;291
8.4.8;References:;291
8.5;CHAPTER 18. MAPPING TECHNIQUES FOR EXPLORATORY PATTERN ANALYSIS;294
8.5.1;1. INTRODUCTION;294
8.5.2;2. WHAT ARE MAPPING METHODS AND HOW ARE THEY USED?;295
8.5.3;3. OVERVIEW;297
8.5.4;4. EXPERIMENTAL COMPARISON;308
8.5.5;5. CONCLUSIONS;315
8.5.6;BIBLIOGRAPHY;315
8.6;CHAPTER 19. A MODEL FOR THE CLASSIFICATION OF CYTOLOGICAL SPECIMENS;318
8.6.1;1. Introduction;318
8.6.2;2. Cell-class and cell-feature approaches;319
8.6.3;3. The inclusion of between-specimen variability: a hierarchicalmodel;320
8.6.4;4. A two-level compound model for specimen classification;322
8.6.5;5. Cell-class approach: a model allowing a random proportion ofabnormal cells;324
8.6.6;6. Cell-feature approach: specimen discriminant analysis;326
8.6.7;7. Conclusions;330
8.6.8;8. References;331
8.7;CHAPTER 20. Astronomical Object Classification;334
8.7.1;1. INTRODUCTION;334
8.7.2;2. CURRENT PROBLEMS IN AUTOMATED ASTRONOMICAL CLASSIFICATION;335
8.7.3;3. CONCLUSIONS;341
8.7.4;References;343
8.8;DISCUSSIONS PART II;346
9;PART III: ARTIFICIAL INTELIGENCEAND PATTERN RECOGNITION;350
9.1;CHAPTER 21. OF BRITTLENESS AND BOTTLENECKS:CHALLENGES IN THE CREATION OF PATTERN-RECOGNITIONAND EXPERT-SYSTEM MODELS;352
9.1.1;1. INTRODUCTION;353
9.1.2;2. THE KNOWLEDGE-ACQUISITION BOTTLENECK;354
9.1.3;3. BRITTLENESS;357
9.1.4;4. DOMAIN MODELING IN PATTERN RECOGNITION;359
9.1.5;5. THE ANALOG OF BRITTLENESS;361
9.1.6;6. DISCUSSION;362
9.1.7;ACKNOWLEDGMENTS;366
9.1.8;REFERENCES;367
9.2;CHAPTER 22. Constructing Alternate Preferred Lines of Reasoning inInconsistent Knowledge Environments;370
9.2.1;Abstract;370
9.2.2;1. Introduction;370
9.2.3;2. Representation;371
9.2.4;3. Knowledge of Uncertainty;372
9.2.5;4. Lines of Reasoning;373
9.2.6;5. Knowledge of Causality;374
9.2.7;6. The Methodology;375
9.2.8;7. Search for the Model-trees;378
9.2.9;8. Extensions of the Method;380
9.2.10;9. Conclusion;382
9.2.11;Bibliography;383
9.3;CHAPTER 23. AN ANALYSIS OF FIVE STRATEGIES FOR REASONING IN UNCERTAINTIES AND THEIR SUITABILITY FOR PATHOLOGY;384
9.3.1;1. INTRODUCTION;385
9.3.2;2. DEFINITIONS AND COMBINATORICS;386
9.3.3;3. ANALYSIS;388
9.3.4;4. CONCLUSION;393
9.3.5;ACKNOWLEDGEMENTS;395
9.3.6;REFERENCES;396
9.4;CHAPTER 24. COMBINING THE CLASSIFICATION RESULTS OF INDEPENDENT CLASSIFIERS BASED ON THE DEMPSTER/SHAFER THEORY OF EVIDENCE;398
9.4.1;1. INTRODUCTION;398
9.4.2;2. COMBINATION PRINCIPLE;399
9.4.3;3. IMPLEMENTATION;400
9.4.4;4. CLASSIFICATION RESULTS;408
9.4.5;5. CONCLUSION;410
9.4.6;REFERENCES;410
9.5;CHAPTER 25. CLUSAN: A KNOWLEDGE BASE FOR APPROXIMATE REASONING IN EXPLORATORY DATA ANALYSIS;412
9.5.1;1. INTRODUCTION;412
9.5.2;2. THE CLUSAN/DELFI EXPERT SYSTEM SET-UP;414
9.5.3;3. LOW-LEVEL CLUSTERING TENDENCY;417
9.5.4;4. PROBLEM EXAMPLES;420
9.5.5;5. CONCLUSIONS;427
9.5.6;REFERENCES;427
9.6;CHAPTER 26. A TWO STEPS DECISION METHOD;430
9.6.1;ABSTRACT.;430
9.6.2;1. DECISION SURFACES TO DECIDE FOR CLASSES WITHIN A CATEGORY;430
9.6.3;2. DECISION BETWEEN CATEGORIES;437
9.6.4;3. CONCLUSION;439
9.6.5;REFERENCES.;440
9.7;CHAPTER 27. A KNOWLEDGE-BASED SYSTEM FOR THETHREEDIMENSIONAL RECONSTRUCTION OF THE CEREBRAL BLOOD VESSELS FROM A PAIR OF STEREOSCOPIC ANGIOGRAMS;442
9.7.1;1. INTRODUCTION;442
9.7.2;2. THE FIRST DELINEATE, THEN MATCH PARADIGM;443
9.7.3;3. BLOOD VESSEL SEGMENT DELINEATION;444
9.7.4;4. HIGH LEVEL FEATURE MATCHING;445
9.7.5;5. CONCLUSION;449
9.7.6;6. ACKNOWLEDGMENTS;452
9.7.7;REFERENCES;452
9.8;CHAPTER 28. PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE IN MOLECULAR BIOLOGY;454
9.8.1;1. INTRODUCTION;454
9.8.2;2. THREE DIMENSIONAL STRUCTURE DETERMINATION;455
9.8.3;3. PRIMARY STRUCTURE (SEQUENCE) ANALYSES;458
9.8.4;4. PREDICTION OF PROTEIN STRUCTURE FROM SEQUENCE;459
9.8.5;5. PLANNING MOLECULAR GENETICS EXPERIMENTS;460
9.8.6;6. CONCLUDING REMARKS;461
9.8.7;ACKNOWLEDGEMENTS;461
9.8.8;REFERENCES;461
9.9;CHAPTER 29. HYPOTHESIS COMBINATION AND CONTEXT SENSITIVE CLASSIFICATION FOR CHROMOSOME ABERRATION SCORING;466
9.9.1;1. INTRODUCTION;466
9.9.2;2. CENTROMERE CANDIDATE HYPOTHESIS GENERATION;470
9.9.3;3. CENTROMERE CANDIDATE FEATURE MEASUREMENT;471
9.9.4;4. CENTROMERE CANDIDATE CLASSIFICATION;472
9.9.5;5. DATA SET COLLECTION AND TRAINING;474
9.9.6;6. RESULTS;474
9.9.7;7. DISCUSSION;475
9.9.8;ACKNOWLEDGEMENTS;476
9.9.9;REFERENCES;476
9.10;CHAPTER 30. AN EXPERT SYSTEM APPROACH TO THE IDENTIFICATION AND CATEGORISATION OF FEATURES OF BIOLOGICAL IMAGES;478
9.10.1;INTRODUCTION;478
9.10.2;POTENTIAL VALUE OF EXPERT SYSTEMS;479
9.10.3;EXAMPLES OF PROJECTS REQUIRING AN EXPERT SYSTEMS APPROACH;479
9.10.4;PROCEDURE FOR FEATURE RECOGNITION OF NEMATODE SECTIONS;483
9.10.5;DESIGN OF THE EXPERT SYSTEM;486
9.10.6;ACKNOWLEDGEMENTS;486
9.10.7;REFERENCES;486
9.11;CHAPTER 31. A Coupled Expert System for Automated Signal Interpretation;488
9.11.1;1. INTRODUCTION;488
9.11.2;2. SYSTEM DESCRIPTION;489
9.11.3;3. SYSTEM'S OPERATION;492
9.11.4;4. APPLICATIONS TO EEG DATA;495
9.11.5;5. DISCUSSION AND CONCLUSIONS;497
9.11.6;ACKNOWLEDGEMENTS;498
9.11.7;REFERENCES;498
9.12;DISCUSSIONS PART III;500
10;AUTHOR INDEX;510
11;SUBJECT INDEX;512