Advances in Imaging and Electron Physics (eBook)
336 Seiten
Elsevier Science (Verlag)
978-0-08-046277-6 (ISBN)
Advances in Imaging and Electron Physics merges two long-running serials-Advances in Electronics and Electron Physics and Advances in Optical and Electron Microscopy. This series features extended articles on the physics of electron devices (especially semiconductor devices), particle optics at high and low energies, microlithography, image science and digital image processing, electromagnetic wave propagation, electron microscopy, and the computing methods used in all these domains.
front cover 1
Title page 4
copyright 5
table of contents 6
front matter 8
Contributors 8
Preface 10
Future Contributions 12
body 18
Recursive Neural Networks and Their Applications to Image Processing 18
Introduction 18
From Flat to Structural Pattern Recognition 18
Recursive Neural Networks: Properties and Applications 24
Recursive Neural Networks 26
Graphs 26
Processing DAGs with Recursive Neural Networks 28
Processing DPAGs 31
Processing DAGs-LE 34
Backpropagation Through Structure 35
Processing Cyclic Graphs 39
Recursive-Equivalent Transforms 42
From Cyclic Graphs to Recursive Equivalent Trees 45
Limitations of the Recursive Neural Network Model 47
Theoretical Conditions for Collision Avoidance 48
Graph-Based Representation of Images 50
Introduction 50
Segmentation of Images 50
Region Adjacency Graphs 53
Multiresolution Trees 55
Object Detection in Images 56
Object Detection Methods 56
Recursive Neural Networks for Detecting Objects in Images 59
Learning Environment Setup 59
Region Adjacency Graphs. 59
Multiresolution Trees. 63
Detecting Objects 64
TV Video Sequences. 66
Images Acquired by an Indoor Camera. 67
Artificial Dataset Generated from COIL-100. 69
References 71
Deterministic Learning and an Application in Optimal Control 78
Introduction 79
Notation 81
A Mathematical Framework for the Learning Problem 82
Statistical Learning 86
Deterministic Learning 91
The Distribution-Free Case 92
Ensuring a Bounded Variation 97
Feedforward Neural Networks 100
Radial Basis Functions 101
Bounds on the Convergence Rate of the ERM Approach 102
The Distribution-Dependent Case 104
The Noisy Case 105
Deterministic Learning for Optimal Control Problems 107
Approximate Dynamic Programming Algorithms 111
T-SO Problems 111
8-SO Problems 113
Approximate Value Iteration 113
Approximate Policy Iteration 114
Performance Issues 115
Deterministic Learning for Dynamic Programming Algorithms 116
The T-SO Case 116
The 8-SO Case 119
Experimental Results 121
Approximation of Unknown Functions 121
Multistage Optimization Tests 124
The Inventory Forecasting Model 125
The Water Reservoir Network Model 126
References 131
X-Ray Fluorescence Holography 136
Introduction 137
Theory 139
Theory Using Simple Models 139
Simulation Using Realistic Models 141
Kossel and X-Ray Standing Wave Lines 145
Removal of Twin Images 146
Multiple Energy Method 147
Two Energy Method 147
Complex Holography 150
Polarization Effect of Incident X-Ray 151
Near Field Effect 153
Experiment and Data Processing 155
Experimental Geometries for Normal and Inverse Modes 155
Laboratory XFH Apparatus 157
Fast X-Ray Fluorescence Detection System at SR 160
Details of Data Processing for Obtaining Atomic Images 162
Sample Cooling Effect 166
Inverse Fourier Analysis 167
Theoretical Proof 167
Demonstration by Experimental Holograms 173
Applications 176
Ultrathin Film 176
Dopants 179
GaAs:Zn 179
Si:Ge 182
Quasicrystal 185
Complex X-Ray Holography 187
Related Methods 191
pXAFS 191
.-Ray Holography 193
Neutron Holography 195
Summary and Outlook 197
References 198
A Taxonomy of Color Image Filtering and Enhancement Solutions 204
Introduction 205
Color Imaging Basics 207
Image Noise 210
Natural Image Noise 210
Noise Modeling 211
Sensor Noise 212
Transmission Noise 214
Color Image Filtering 216
Noise-Reduction Techniques 219
Order-Statistic Theory for Color Vectors 219
Component-Wise Median Filters 222
Vector Median Filters 224
Vector Directional Filters 229
Selection Weighted Vector Filters 232
Data-Adaptive Vector Filters 235
Adaptive Multichannel Filters Based on Digital Paths 237
Switching Filtering Schemes 240
Similarity Based Vector Filters 243
Adaptive Hybrid Vector Filters 245
Performance Evaluation of the Noise Reduction Filters 248
Objective Evaluation 248
Subjective Evaluation 250
Inpainting Techniques 251
Image Sharpening Techniques 252
Image Zooming Techniques 256
Applications 258
Virtual Restoration of Artworks 258
Television Image Enhancement 260
Edge Detection 261
Scalar Operators 262
Gradient Operators 265
Zero-Crossing-Based Operators 266
Vector Operators 267
Evaluation Criteria 270
Objective Evaluation Approach 271
Subjective Evaluation Approach 272
Conclusion 274
References 274
General Sweep Mathematical Morphology 282
Introduction 282
Theoretical Development of General Sweep Mathematical Morphology 285
Computation of Traditional Morphology 285
General Sweep Mathematical Morphology 287
Properties of Sweep Morphological Operations 290
Blending of Swept Surfaces with Deformations 292
Image Enhancement 295
Edge Linking 297
Edge Linking Using Sweep Morphology 298
Shortest Path Planning for Mobile Robot 303
Geometric Modeling and Sweep Mathematical Morphology 305
Tolerance Expression 306
Sweep Surface Modeling 308
Formal Language and Sweep Morphology 308
Representation Scheme 309
Two-Dimensional Attributes 309
Three-Dimensional Attributes 310
Grammars 314
Two-Dimensional Attributes 315
Three-Dimensional Attributes 315
Parsing Algorithm 317
Conclusions 320
References 320
Further Reading 323
Index 324
REFERENCES
Aho A, Hopcroft J, Ullman J. Data Structures and Algorithms. Reading, MA: Addison-Wesley; 1983.
Bengio Y, Frasconi P, Simard P. Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 1994;5:157–166.
Bezdek J. What is computational intelligence?. In: Computational Intelligence: Imitating Life. New York: IEEE Press; 1994:1–12.
Bianchini M, Gori M, Scarselli F. Theoretical properties of recursive networks with linear neurons. IEEE Trans. Neural Netw. 2001a;12(5):953–967.
Bianchini M, Gori M, Scarselli F. Processing directed acyclic graphs with recursive neural networks. IEEE Trans. Neural Netw. 2001b;12(6):1464–1470.
Bianchini M, Gori M, Scarselli F. Recursive processing of cyclic graphs. In: Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN 2002); 2002:154–159.
Bianchini M, Mazzoni P, Sarti L, Scarselli F. Face spotting in color images using recursive neural networks. In: Gori M, Marinai S, eds. IAPR—TC3 International Workshop on Artificial Neural Networks in Pattern Recognition (Florence, Italy). 2003a.
Bianchini M, Gori M, Mazzoni P, Sarti L, Scarselli F. Face localization with recursive neural networks. In: Marinaro M, Tagliaferri R, eds. Neural Nets—WIRN '03, Vietri (Salerno, Italy). Berlin: Springer; 2003b.
Bianchini M, Gori M, Sarti L, Scarselli F. Backpropagation through cyclic structures. In: Cappelli A, Turini F, eds. LNAI — AI*IA 2003: Advances in Artificial Intelligence (Pisa, Italy). Berlin: Springer; 2003c:118–129. LNCS..
Bianchini M, Maggini M, Sarti L, Scarselli F. Recursive neural networks for processing graphs with labelled edges. In: Proceedings of ESANN 2004 (Bruges, Belgium); 2004a:325–330.
Bianchini M, Maggini M, Sarti L, Scarselli F. Recursive neural networks for object detection. In: Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN 2004); 2004b:1911–1915.
Bianchini M, Maggini M, Sarti L, Scarselli F. Recursive neural networks for processing graphs with labelled edges: Theory and applications. Neural Netw. 2005a;18:1040–1050.
Bianchini M, Maggini M, Sarti L, Scarselli F. Recursive neural networks learn to localize faces. Pattern Recognit. Lett. 2005b;26:1885–1895.
Bianchini M, Gori M, Sarti L, Scarselli F. Recursive processing of cyclic graphs. IEEE Trans. Neural Netw. 2006;17:10–18.
Bianucci A, Micheli A, Sperduti A, Starita A. Analysis of the internal representations developed by neural networks for structures applied to quantitative structure-activity relationship studies of benzodiazepines. Chem. Info. and Comp. Sci. 2001;41(1):202–218.
Boser B, Guyon I, Vapnik V. A training algorithm for optimal margin classifiers. In: Haussler D, ed. Proceedings of the 5th Annual ACM Workshop on Computational Learning Theory. New York: ACM Press; 1992:144–152.
Carleson A, Cumby C, Rosen J, Roth D. The SNoW learning architecture. Tech. Rep. UIUCDCS-R-99-2101, University of Illinois at Urbana–Campaign, Computer Science Department; 1999.
Chappell G, Taylor J. The temporal Kohonen map. Neural Netw. 1993;6:441–445.
Cheng HD, Yang XH, Sun Y, Wang JL. Color image segmentation: Advances and prospects. Pattern Recognit. 2001;34:2259–2281.
Collins M, Duffy N. Convolution kernels for natural language. In: Dietterich T, Becker S, Ghahramani Z, eds. Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press; 2002.
de Mauro C, Diligenti M, Gori M, Maggini M. Similarity learning for graph based image representation. Pattern Recognit. Lett. 2003;24(8):1115–1122.
Diligenti M, Gori M, Maggini M, Martinelli E. Adaptive graphical pattern recognition for the classification of company logos. Pattern Recognit. 2001;34:2049–2061.
Duda R, Hart P. Pattern Classification and Scene Analysis. New York: Wiley; 1973.
Elman J. Finding structure in time. Cog. Sci. 1990;14:179–211.
Euliano N, Principe J. A spatiotemporal memory based on SOMs with activity diffusion. In: Oja E, Kaski S, eds. Kohonen Maps. Amsterdam: Elsevier; 1999.
Farkas I, Mikkulainen R. Modeling the self-organization of directional selectivity in the primary visual cortex. In: Proceedings of the International Conference on Artificial Neural Networks. Springer; 1999:251–256.
Frasconi P, Gori M, Sperduti A. A general framework for adaptive processing of data structures. IEEE Trans. Neural Netw. 1998;9(5):768–786.
Fu K, Mui JK. A survey on image segmentation. Pattern Recognit. 1981;13:3–16.
Gärtner T. A survey of kernels for structured data. SIGKDD Explorations. 2003;5(1):49–58.
Gärtner T, Flach P, Wrobel S. On graph kernels: Hardness results and efficient alternatives. In: Proceedings of the 16th Annual Conference on Computational Learning Theory and the 7th Kernel Workshop; 2003:129–143.
Gori M, Maggini M, Sarti L. A recursive neural network model for processing directed acyclic graphs with labeled edges. In: Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN 2003); 2003:1351–1355.
Gori M, Hagenbuchner M, Scarselli F, Tsoi A-C. Graphical-based learning environment for pattern recognition. In: Proceedings of SSPR 2004; 2004.
Gori M, Maggini M, Sarti L. Exact and approximate graph matching using random walks. IEEE Trans. Pattern Anal. Mach. Intell. 2005a;27(7):1100–1111.
Gori M, Monfardini G, Scarselli F. A new model for learning in graph domains. 729–734. Proceedings of IJCNN 2005. 2005b;vol. 2.
Günter S, Bunke H. Validation indices for graph clustering. In: Jolion J.-M., Kropatsch W, Vento M, eds. Proceedings of the Third IAPR-TC15 Workshop on Graph-based Representations in Pattern Recognition; 2001:229–238.
Hagenbuchner M, Tsoi A-C, Sperduti A. A supervised selforganizing map for structured data. In: Allison LAN, Yin H, Slack J, eds. Advances in Self-Organizing Maps. Berlin: Springer; 2001:21–28.
Hagenbuchner M, Sperduti A, Tsoi A-C. A self-organizing map for adaptive processing of structured data. IEEE Trans. Neural Netw. 2003;14(3):491–505.
Hammer B. On the approximation capability of recurrent neural networks. In: NC'98, International Symposium on Neural Computation (Vienna, Austria); 1998.
Hammer B. Approximation capabilities of folding networks. In: ESANN '99 (Bruges, Belgium). 1999:33–38.
Hammer B, Micheli A, Stricker M, Sperduti A. A general framework for unsupervised processing of structured data. Neurocomputing. 2004;57:3–35.
Haralick R, Shapiro L. Image segmentation techniques. Comput. Vision, Graph. Image Process. 1985;29:100–132.
Healey G, Binford T. Using color for geometry-insensitive segmentation. J. Opt. Soc. Am. 1989;22(1):920–937.
Hoekstra A, Drossaers M. An extended Kohonen feature map for sentence recognition. In: Gielen S, Kappen B, eds. Proceedings of the International Conference on Artificial Neural Networks. Berlin: Springer; 1993:404–407.
Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Netw. 1989;2:359–366.
Hunter GM, Steiglitz K. Operations on images using quadtrees. IEEE Trans. Pattern Anal. Mach. Intell. 1979;1:145–153.
James D, Mikkulainen R. SARDNET: A self-organizing feature map for sequences. In: Tesauro G, Touretzky D, Leen T, eds. Cambridge, MA: MIT Press; 577–584. Advances in Neural Information Processing Systems. 1995;vol. 7.
Kangas T. Time-delayed self-organizing maps. 331–336. Proceedings of IEEE/INNS IJCNN. 1990;vol. 2.
Kohonen T, Sommervuo P. How to make large self-organizing maps for nonvectorial data. Neural Netw. 2002;15(8–9):945–952.
Koskela T, Varsta M, Heikkonen J, Kaski K. Recurrent SOM with local linear models in time series prediction. In: Verleysen M, ed. Proceedings of the 6th European Symposium on Artificial Neural Networks; 1998a:167–172.
Koskela T, Varsta M, Heikkonen J, Kaski K. Time series prediction using recurrent SOM with local linear models. Proceedings of the Int. J. Conf. of Knowledge-Based Intelligent Engineering Systems. 1998b;2(1):60–68.
Küchler A, Goller C. Inductive learning in symbolic domains using structure-driven recurrent neural networks. In: Görz G, Hölldobler S, eds. Advances in Artificial Intelligence. Berlin: Springer; 1996:183–197.
Leung TK, Burl MC, Perona P....
| Erscheint lt. Verlag | 29.7.2011 |
|---|---|
| Sprache | englisch |
| Themenwelt | Sachbuch/Ratgeber |
| Mathematik / Informatik ► Informatik | |
| Naturwissenschaften ► Physik / Astronomie ► Elektrodynamik | |
| Technik ► Bauwesen | |
| Technik ► Elektrotechnik / Energietechnik | |
| Technik ► Maschinenbau | |
| ISBN-10 | 0-08-046277-4 / 0080462774 |
| ISBN-13 | 978-0-08-046277-6 / 9780080462776 |
| Haben Sie eine Frage zum Produkt? |
EPUB (Adobe DRM)Kopierschutz: Adobe-DRM
Adobe-DRM ist ein Kopierschutz, der das eBook vor Mißbrauch schützen soll. Dabei wird das eBook bereits beim Download auf Ihre persönliche Adobe-ID autorisiert. Lesen können Sie das eBook dann nur auf den Geräten, welche ebenfalls auf Ihre Adobe-ID registriert sind.
Details zum Adobe-DRM
Dateiformat: EPUB (Electronic Publication)
EPUB ist ein offener Standard für eBooks und eignet sich besonders zur Darstellung von Belletristik und Sachbüchern. Der Fließtext wird dynamisch an die Display- und Schriftgröße angepasst. Auch für mobile Lesegeräte ist EPUB daher gut geeignet.
Systemvoraussetzungen:
PC/Mac: Mit einem PC oder Mac können Sie dieses eBook lesen. Sie benötigen eine
eReader: Dieses eBook kann mit (fast) allen eBook-Readern gelesen werden. Mit dem amazon-Kindle ist es aber nicht kompatibel.
Smartphone/Tablet: Egal ob Apple oder Android, dieses eBook können Sie lesen. Sie benötigen eine
Geräteliste und zusätzliche Hinweise
Buying eBooks from abroad
For tax law reasons we can sell eBooks just within Germany and Switzerland. Regrettably we cannot fulfill eBook-orders from other countries.
aus dem Bereich
