Digital Image Processing
Autor Mahmood R. Azimi-Sadjadien Limba Engleză Hardback – 25 oct 2026
Engineers and researchers implementing image processing systems need methods that bridge classical techniques with modern machine learning approaches. This book delivers both traditional and modern AI-based methods and algorithms in image enhancement, restoration, segmentation, compression, and analysis. Written by an educator and researcher with more than 40 years' experience in signal/image processing and machine learning, this reference provides theoretical and practical tools using the Python platform for a wide range of applications.
The book consists of twenty chapters covering fundamental and advanced topics including two-dimensional image modeling, wavelet transform, Kalman filters, image reconstruction and computerized tomography, layered machines, linear and nonlinear autoencoders, and associative memories. Each chapter includes practical examples demonstrating real-world applications, supported by Python code, solution manuals, and presentation materials.
This book also covers:
- Fundamental supervised and unsupervised machine learning methods with specific deep learning applications for image enhancement, segmentation, feature extraction, data compression, and classification
- Wavelet transform and filter banks integrated with state-of-the-art image analysis and processing
- Advanced filtering techniques including Wiener and Kalman filters, and two-dimensional image modeling
- Python implementations via Google colab platform enabling immediate application of theoretical concepts to practical image processing problems
- Instructor resources including solution manuals and presentation materials supporting adoption in digital image processing and computer vision courses
Preț: 748.36 lei
Preț vechi: 971.89 lei
-23% Nou
Puncte Express: 1123
Carte indisponibilă temporar
Doresc să fiu notificat când acest titlu va fi disponibil:
Se trimite...
Specificații
ISBN-13: 9781394240449
ISBN-10: 1394240449
Pagini: 512
Dimensiuni: 152 x 229 mm
Editura: John Wiley & Sons, Inc.
Locul publicării:Chichester, United Kingdom
ISBN-10: 1394240449
Pagini: 512
Dimensiuni: 152 x 229 mm
Editura: John Wiley & Sons, Inc.
Locul publicării:Chichester, United Kingdom
Notă biografică
MAHMOOD R. AZIMI-SADJADI received his MS and PhD degrees from the Imperial College of Science and Technology, University of London, UK. He is a Full Professor in the Department of Electrical and Computer Engineering, and Director of the Digital Signal/Image Processing Laboratory at Colorado State University, USA. His research spans statistical signal and image processing, machine learning algorithms and applications, and adaptive systems. A life member of IEEE who served as Associate Editor for IEEE Transactions on Signal Processing and Neural Networks, Mahmood received the 1999 Abell Faculty Teaching Award of Excellence from the College of Engineering.
Cuprins
Preface xvii
About the Book xvii
Prerequisites and Course Organization xviii
Acknowledgments xviii
About the Author xix
Conventions and Notations xxi
About the Companion Website xxiii
1 Introduction 1
1.1 DIP System Components 4
1.2 Areas of DIP 5
1.3 Final Remarks and Goals 7
2 Review of 1-D Signal Processing 9
2.1 Discrete-Time Signals and Systems-Deterministic Case 9
2.2 Discrete-Time Signals and Systems-Random Case 20
2.3 Problems 28
3 Theoretical Background 31
3.1 Discrete-Space 2-D Signals and Systems-Deterministic Case 31
3.2 Discrete-space 2-D Signals and Systems-Random Case 45
3.3 Computer Projects 49
3.4 Problems 50
4 Image Formation and Perception 53
4.1 Human Eye 53
4.2 Elements of Visual Perception 54
4.3 Color Systems 61
4.4 Problems 64
5 Image Sampling and Quantization 67
5.1 Image Sampling 67
5.2 Image Quantization 72
5.3 Computer Projects 81
5.4 Problems 82
6 Image Transforms 85
6.1 2-D Discrete Fourier Transform 85
6.2 2-D Discrete Cosine Transform 87
6.3 2-D Walsh-Hadamard Transform 90
6.4 2-D Karhunen-Loeve Transform 96
6.5 Computer Projects 101
6.6 Problems 102
7 Wavelet Transform 107
7.1 Short-Time Fourier Transform 107
7.2 Continuous Wavelet Transform 109
7.3 Digitization of Shift-Scale Parameters and Wavelet Series 114
7.4 Filter Banks and Discrete Wavelet Series 115
7.5 2-D DWT and Filter Banks 123
7.6 Computer Projects 126
7.7 Problems 127
8 Image Enhancement 131
8.1 Point Operations 131
8.2 Spatial Operations 139
8.3 Transform Domain Operations 154
8.4 Computer Projects 162
8.5 Problems 164
9 Image Modeling 171
9.1 1-D Linear Models 171
9.2 2-D Linear Image Models 178
9.3 Multivariate or Vector Linear Models 188
9.4 Computer Projects 191
9.5 Problems 191
10 Image Restoration 195
10.1 Image Degradation Models 195
10.2 Image Restoration Filters 197
10.3 Computer Projects 216
10.4 Problems 217
11 Image Compression and Encoding 223
11.1 A Review of Information Theory 224
11.2 Image Compression and Encoding Methods - Lossless 227
11.3 Image Compression and Encoding Methods - Lossy 232
11.4 Hybrid Methods 242
11.5 Computer Projects 242
11.6 Problems 243
12 Image Segmentation 249
12.1 Similarity-Based Image Segmentation 250
12.2 Edge and Contour-Based Segmentation 264
12.3 Computer Projects 269
12.4 Problems 271
13 Feature Extraction 275
13.1 Objectives and Requirements 275
13.2 Color Features 277
13.3 Energy Features 279
13.4 Spectral Features 280
13.5 Textural Features 283
13.6 Line and Contour Features 291
13.7 Shape Features 301
13.8 Computer Projects 305
13.9 Problems 307
14 Morphological Operations 311
14.1 Basic Morphological Operations - Binary Images 312
14.2 Morphological Transforms - Binary Images 316
14.3 Morphological Operations - Grayscale Images 322
14.4 Applications of Morphological Operations 328
14.5 Computer Projects 332
14.6 Problems 334
15 Image Reconstruction 339
15.1 Basics of Image Reconstruction 339
15.2 Analytical Image Reconstruction Methods 344
15.3 Iterative Image Reconstruction Methods 347
15.4 Computer Projects 354
15.5 Problems 354
16 Traditional Image Classification 359
16.1 Deterministic Pattern Classification 359
16.2 Statistical Pattern Classification 363
16.3 Computer Projects 371
16.4 Problems 371
17 Modern Image Classification: Elements of Machine Learning 375
17.1 Biological Neural Networks 375
17.2 Artificial Neural Networks 376
17.3 Learning Algorithms 379
17.4 Computer Projects 395
17.5 Problems 396
18 Modern Image Classification-Layered Machines 401
18.1 Multilayer Perceptron Neural Networks 401
18.2 Convolutional Neural Networks 408
18.3 Self-Organizing Feature Maps 417
18.4 Computer Projects 424
18.5 Problems 425
19 Dimensionality Reduction Networks and Autoencoders 431
19.1 Linear Autoencoders 431
19.2 Nonlinear Dimensionality Reduction Using Manifold Learning 434
19.3 Nonlinear Autoencoders 438
19.4 Computer Projects 444
19.5 Problems 445
20 AI Applications in Digital Image Processing 449
20.1 Disparity Estimation from Stereo Images 449
20.2 Associative Memory for Pattern Retrieval 453
20.3 Computer Projects 461
References 462
Appendix-A: Review of 1-D z-Transform 465
Appendix-B: 2-D z-Transform 471
Index 473
About the Book xvii
Prerequisites and Course Organization xviii
Acknowledgments xviii
About the Author xix
Conventions and Notations xxi
About the Companion Website xxiii
1 Introduction 1
1.1 DIP System Components 4
1.2 Areas of DIP 5
1.3 Final Remarks and Goals 7
2 Review of 1-D Signal Processing 9
2.1 Discrete-Time Signals and Systems-Deterministic Case 9
2.2 Discrete-Time Signals and Systems-Random Case 20
2.3 Problems 28
3 Theoretical Background 31
3.1 Discrete-Space 2-D Signals and Systems-Deterministic Case 31
3.2 Discrete-space 2-D Signals and Systems-Random Case 45
3.3 Computer Projects 49
3.4 Problems 50
4 Image Formation and Perception 53
4.1 Human Eye 53
4.2 Elements of Visual Perception 54
4.3 Color Systems 61
4.4 Problems 64
5 Image Sampling and Quantization 67
5.1 Image Sampling 67
5.2 Image Quantization 72
5.3 Computer Projects 81
5.4 Problems 82
6 Image Transforms 85
6.1 2-D Discrete Fourier Transform 85
6.2 2-D Discrete Cosine Transform 87
6.3 2-D Walsh-Hadamard Transform 90
6.4 2-D Karhunen-Loeve Transform 96
6.5 Computer Projects 101
6.6 Problems 102
7 Wavelet Transform 107
7.1 Short-Time Fourier Transform 107
7.2 Continuous Wavelet Transform 109
7.3 Digitization of Shift-Scale Parameters and Wavelet Series 114
7.4 Filter Banks and Discrete Wavelet Series 115
7.5 2-D DWT and Filter Banks 123
7.6 Computer Projects 126
7.7 Problems 127
8 Image Enhancement 131
8.1 Point Operations 131
8.2 Spatial Operations 139
8.3 Transform Domain Operations 154
8.4 Computer Projects 162
8.5 Problems 164
9 Image Modeling 171
9.1 1-D Linear Models 171
9.2 2-D Linear Image Models 178
9.3 Multivariate or Vector Linear Models 188
9.4 Computer Projects 191
9.5 Problems 191
10 Image Restoration 195
10.1 Image Degradation Models 195
10.2 Image Restoration Filters 197
10.3 Computer Projects 216
10.4 Problems 217
11 Image Compression and Encoding 223
11.1 A Review of Information Theory 224
11.2 Image Compression and Encoding Methods - Lossless 227
11.3 Image Compression and Encoding Methods - Lossy 232
11.4 Hybrid Methods 242
11.5 Computer Projects 242
11.6 Problems 243
12 Image Segmentation 249
12.1 Similarity-Based Image Segmentation 250
12.2 Edge and Contour-Based Segmentation 264
12.3 Computer Projects 269
12.4 Problems 271
13 Feature Extraction 275
13.1 Objectives and Requirements 275
13.2 Color Features 277
13.3 Energy Features 279
13.4 Spectral Features 280
13.5 Textural Features 283
13.6 Line and Contour Features 291
13.7 Shape Features 301
13.8 Computer Projects 305
13.9 Problems 307
14 Morphological Operations 311
14.1 Basic Morphological Operations - Binary Images 312
14.2 Morphological Transforms - Binary Images 316
14.3 Morphological Operations - Grayscale Images 322
14.4 Applications of Morphological Operations 328
14.5 Computer Projects 332
14.6 Problems 334
15 Image Reconstruction 339
15.1 Basics of Image Reconstruction 339
15.2 Analytical Image Reconstruction Methods 344
15.3 Iterative Image Reconstruction Methods 347
15.4 Computer Projects 354
15.5 Problems 354
16 Traditional Image Classification 359
16.1 Deterministic Pattern Classification 359
16.2 Statistical Pattern Classification 363
16.3 Computer Projects 371
16.4 Problems 371
17 Modern Image Classification: Elements of Machine Learning 375
17.1 Biological Neural Networks 375
17.2 Artificial Neural Networks 376
17.3 Learning Algorithms 379
17.4 Computer Projects 395
17.5 Problems 396
18 Modern Image Classification-Layered Machines 401
18.1 Multilayer Perceptron Neural Networks 401
18.2 Convolutional Neural Networks 408
18.3 Self-Organizing Feature Maps 417
18.4 Computer Projects 424
18.5 Problems 425
19 Dimensionality Reduction Networks and Autoencoders 431
19.1 Linear Autoencoders 431
19.2 Nonlinear Dimensionality Reduction Using Manifold Learning 434
19.3 Nonlinear Autoencoders 438
19.4 Computer Projects 444
19.5 Problems 445
20 AI Applications in Digital Image Processing 449
20.1 Disparity Estimation from Stereo Images 449
20.2 Associative Memory for Pattern Retrieval 453
20.3 Computer Projects 461
References 462
Appendix-A: Review of 1-D z-Transform 465
Appendix-B: 2-D z-Transform 471
Index 473