Table of contents : Front Cover......Page 1 Image Processing and Pattern Recognition......Page 4 Copyright Page......Page 5 Contents......Page 6 Contributors......Page 14 Preface......Page 16 I. Introduction......Page 22 II. Pattern Recognition Problem......Page 24 III. Neural Networks in Feature Extraction......Page 32 IV. Classification Methods: Statistical and Neural......Page 41 V. Neural Network Applications in Pattern Recognition......Page 59 VI. Summary......Page 73 References......Page 74 I. Introduction......Page 82 II. Applications......Page 84 III. Data Acquisition and Preprocessing......Page 85 IV. Statistical Classifiers......Page 86 V. Neural Classifiers......Page 95 VI. Literature Survey......Page 100 VII. Simulation Results......Page 102 VIII. Conclusions......Page 106 References......Page 107 I. Introduction......Page 110 II. Review of Artificial Neural Network Applications in Medical Imaging......Page 116 III. Segmentation of Arteriograms......Page 120 IV. Back-Propagation Artificial Neural Network for Arteriogram Segmentation: A Supervised Approach......Page 122 V. Self-Adaptive Artificial Neural Network for Arteriogram Segmentation: An Unsupervised Approach......Page 128 VI. Conclusions......Page 145 References......Page 150 I. Introduction......Page 154 II. Small-Size Neuro-Recognition Technique Using the Masks......Page 155 III. Mask Determination Using the Genetic Algorithm......Page 164 IV. Development of the Neuro-Recognition Board Using the Digital Signal Processor......Page 173 V. Unification of Three Core Techniques......Page 177 VI. Conclusions......Page 179 References......Page 180 I. Introduction......Page 182 II. Classification Paradigms......Page 185 III. Neural Network Classifiers......Page 188 IV. Classification Reliability......Page 193 V. Evaluating Neural Network Classification Reliability......Page 195 VI. Finding a Reject Rule......Page 199 VII. Experimental Results......Page 206 VIII. Summary......Page 217 References......Page 218 I. Introduction......Page 222 II. Physiological Background......Page 223 III. Regularization Vision Chips......Page 242 IV. Spatio-Temporal Stability of Vision Chips......Page 285 References......Page 304 I. Introduction......Page 308 II. Quasi-Newton Methods for Neural Network Training......Page 310 III. Selecting the Number of Output Units......Page 316 IV. Determining the Number of Hidden Units......Page 317 V. Selecting the Number of Input Units......Page 324 VI. Determining the Network Connections by Pruning......Page 330 VII. Applications of Neural Networks to Data Mining......Page 334 VIII. Summary......Page 337 References......Page 338 I. Introduction......Page 342 II. Adaptive Learning Algorithm......Page 345 III. Simulation Results......Page 356 IV. Applications......Page 364 V. Conclusion......Page 370 VI. Appendix......Page 371 References......Page 372 I. Introduction......Page 374 II. Complexity Regularization......Page 378 III. Sensitivity Calculation......Page 383 IV. Optimization through Constraint Satisfaction......Page 389 V. Local and Distributed Bottlenecks......Page 393 VI. Interactive Pruning......Page 395 VII. Other Pruning Methods......Page 397 References......Page 399 Index......Page 404