{"product_id":"object-detection-and-recognition-in-digital-images-theory-and-practice-hardback-9780470976371","title":"Object Detection and Recognition in Digital Images; Theory and Practice (Hardback) 9780470976371","description":"\u003cfont face=\"Georgia\"\u003e\r\n\u003cp\u003e\u003cfont size=\"6\"\u003eObject Detection and Recognition in Digital Images\u003c\/font\u003e\u003cbr\u003e\r\n\u003cfont size=\"5\"\u003eTheory and Practice\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\r\n\r\n\r\n\u003cp\u003e\u003cfont size=\"4\"\u003eBoguslaw Cyganek (Author)\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e9780470976371, Wiley\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003eHardback, published 23 July 2013\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e560 pages\u003cbr\u003e25.2 x 17.9 x 3.3 cm, 1.016 kg\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\r\n\r\n\r\n\r\n\u003cp align=\"justify\"\u003e\u003cstrong\u003e\u003cfont size=\"3\"\u003eObject detection, tracking and recognition in images are key problems in computer vision. This book provides the reader with a balanced treatment between the theory and practice of selected methods in these areas to make the book accessible to a range of researchers, engineers, developers and postgraduate students working in computer vision and related fields. \u003cp\u003eKey features:\u003c\/p\u003e \u003cul\u003e \u003cli\u003eExplains the main theoretical ideas behind each method (which are augmented with a rigorous mathematical derivation of the formulas), their implementation (in C++) and demonstrated working in real applications.\u003c\/li\u003e \u003cli\u003ePlaces an emphasis on tensor and statistical based approaches within object detection and recognition.\u003c\/li\u003e \u003cli\u003eProvides an overview of image clustering and classification methods which includes subspace and kernel based processing, mean shift and Kalman filter, neural networks, and k-means methods.\u003c\/li\u003e \u003cli\u003eContains numerous case study examples of mainly automotive applications.\u003c\/li\u003e \u003cli\u003eIncludes a companion website hosting full C++ implementation, of topics presented in the book as a software library, and an accompanying manual to the software platform.\u003c\/li\u003e \u003c\/ul\u003e\u003c\/font\u003e\u003c\/strong\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e\u003cp\u003ePreface xiii\u003c\/p\u003e \u003cp\u003eAcknowledgements xv\u003c\/p\u003e \u003cp\u003eNotations and Abbreviations xvii\u003c\/p\u003e \u003cp\u003e\u003cb\u003e1 Introduction 1\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e1.1 A Sample of Computer Vision 3\u003c\/p\u003e \u003cp\u003e1.2 Overview of Book Contents 6\u003c\/p\u003e \u003cp\u003eReferences 8\u003c\/p\u003e \u003cp\u003e\u003cb\u003e2 Tensor Methods in Computer Vision 9\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e2.1 Abstract 9\u003c\/p\u003e \u003cp\u003e2.2 Tensor – A Mathematical Object 10\u003c\/p\u003e \u003cp\u003e2.2.1 Main Properties of Linear Spaces 10\u003c\/p\u003e \u003cp\u003e2.2.2 Concept of a Tensor 11\u003c\/p\u003e \u003cp\u003e2.3 Tensor – A Data Object 13\u003c\/p\u003e \u003cp\u003e2.4 Basic Properties of Tensors 15\u003c\/p\u003e \u003cp\u003e2.4.1 Notation of Tensor Indices and Components 16\u003c\/p\u003e \u003cp\u003e2.4.2 Tensor Products 18\u003c\/p\u003e \u003cp\u003e2.5 Tensor Distance Measures 20\u003c\/p\u003e \u003cp\u003e2.5.1 Overview of Tensor Distances 22\u003c\/p\u003e \u003cp\u003e2.5.1.1 Computation of Matrix Exponent and Logarithm Functions 24\u003c\/p\u003e \u003cp\u003e2.5.2 Euclidean Image Distance and Standardizing Transform 29\u003c\/p\u003e \u003cp\u003e2.6 Filtering of Tensor Fields 33\u003c\/p\u003e \u003cp\u003e2.6.1 Order Statistic Filtering of Tensor Data 33\u003c\/p\u003e \u003cp\u003e2.6.2 Anisotropic Diffusion Filtering 36\u003c\/p\u003e \u003cp\u003e2.6.3 IMPLEMENTATION of Diffusion Processes 40\u003c\/p\u003e \u003cp\u003e2.7 Looking into Images with the Structural Tensor 44\u003c\/p\u003e \u003cp\u003e2.7.1 Structural Tensor in Two-Dimensional Image Space 47\u003c\/p\u003e \u003cp\u003e2.7.2 Spatio-Temporal Structural Tensor 50\u003c\/p\u003e \u003cp\u003e2.7.3 Multichannel and Scale-Space Structural Tensor 52\u003c\/p\u003e \u003cp\u003e2.7.4 Extended Structural Tensor 54\u003c\/p\u003e \u003cp\u003e2.7.4.1 IMPLEMENTATION of the Linear and Nonlinear Structural Tensor 57\u003c\/p\u003e \u003cp\u003e2.8 Object Representation with Tensor of Inertia and Moments 62\u003c\/p\u003e \u003cp\u003e2.8.1 IMPLEMENTATION of Moments and their Invariants 65\u003c\/p\u003e \u003cp\u003e2.9 Eigendecomposition and Representation of Tensors 68\u003c\/p\u003e \u003cp\u003e2.10 Tensor Invariants 72\u003c\/p\u003e \u003cp\u003e2.11 Geometry of Multiple Views: The Multifocal Tensor 72\u003c\/p\u003e \u003cp\u003e2.12 Multilinear Tensor Methods 75\u003c\/p\u003e \u003cp\u003e2.12.1 Basic Concepts of Multilinear Algebra 78\u003c\/p\u003e \u003cp\u003e2.12.1.1 Tensor Flattening 78\u003c\/p\u003e \u003cp\u003e2.12.1.2 IMPLEMENTATION Tensor Representation 84\u003c\/p\u003e \u003cp\u003e2.12.1.3 The k-mode Product of a Tensor and a Matrix 95\u003c\/p\u003e \u003cp\u003e2.12.1.4 Ranks of a Tensor 100\u003c\/p\u003e \u003cp\u003e2.12.1.5 IMPLEMENTATION of Basic Operations on Tensors 101\u003c\/p\u003e \u003cp\u003e2.12.2 Higher-Order Singular Value Decomposition (HOSVD) 112\u003c\/p\u003e \u003cp\u003e2.12.3 Computation of the HOSVD 114\u003c\/p\u003e \u003cp\u003e2.12.3.1 Implementation of the HOSVD Decomposition 119\u003c\/p\u003e \u003cp\u003e2.12.4 HOSVD Induced Bases 121\u003c\/p\u003e \u003cp\u003e2.12.5 Tensor Best Rank-1 Approximation 123\u003c\/p\u003e \u003cp\u003e2.12.6 Rank-1 Decomposition of Tensors 126\u003c\/p\u003e \u003cp\u003e2.12.7 Best Rank-(R1, R2, . . . , RP) Approximation 131\u003c\/p\u003e \u003cp\u003e2.12.8 Computation of the Best Rank-(R1, R2, . . . , RP) Approximations 134\u003c\/p\u003e \u003cp\u003e2.12.8.1 IMPLEMENTATION – Rank Tensor Decompositions 137\u003c\/p\u003e \u003cp\u003e2.12.8.2 CASE STUDY – Data Dimensionality Reduction 145\u003c\/p\u003e \u003cp\u003e2.12.9 Subspace Data Representation 149\u003c\/p\u003e \u003cp\u003e2.12.10 Nonnegative Matrix Factorization 151\u003c\/p\u003e \u003cp\u003e2.12.11 Computation of the Nonnegative Matrix Factorization 155\u003c\/p\u003e \u003cp\u003e2.12.12 Image Representation with NMF 160\u003c\/p\u003e \u003cp\u003e2.12.13 Implementation of the Nonnegative Matrix Factorization 162\u003c\/p\u003e \u003cp\u003e2.12.14 Nonnegative Tensor Factorization 169\u003c\/p\u003e \u003cp\u003e2.12.15 Multilinear Methods of Object Recognition 173\u003c\/p\u003e \u003cp\u003e2.13 Closure 179\u003c\/p\u003e \u003cp\u003e2.13.1 Chapter Summary 179\u003c\/p\u003e \u003cp\u003e2.13.2 Further Reading 180\u003c\/p\u003e \u003cp\u003e2.13.3 Problems and Exercises 181\u003c\/p\u003e \u003cp\u003eReferences 182\u003c\/p\u003e \u003cp\u003e\u003cb\u003e3 Classification Methods and Algorithms 189\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e3.1 Abstract 189\u003c\/p\u003e \u003cp\u003e3.2 Classification Framework 190\u003c\/p\u003e \u003cp\u003e3.2.1 IMPLEMENTATION Computer Representation of Features 191\u003c\/p\u003e \u003cp\u003e3.3 Subspace Methods for Object Recognition 194\u003c\/p\u003e \u003cp\u003e3.3.1 Principal Component Analysis 195\u003c\/p\u003e \u003cp\u003e3.3.1.1 Computation of the PCA 199\u003c\/p\u003e \u003cp\u003e3.3.1.2 PCA for Multi-Channel Image Processing 210\u003c\/p\u003e \u003cp\u003e3.3.1.3 PCA for Background Subtraction 214\u003c\/p\u003e \u003cp\u003e3.3.2 Subspace Pattern Classification 215\u003c\/p\u003e \u003cp\u003e3.4 Statistical Formulation of the Object Recognition 222\u003c\/p\u003e \u003cp\u003e3.4.1 Parametric and Nonparametric Methods 222\u003c\/p\u003e \u003cp\u003e3.4.2 Probabilistic Framework 222\u003c\/p\u003e \u003cp\u003e3.4.3 Bayes Decision Rule 223\u003c\/p\u003e \u003cp\u003e3.4.4 Maximum a posteriori Classification Scheme 224\u003c\/p\u003e \u003cp\u003e3.4.5 Binary Classification Problem 226\u003c\/p\u003e \u003cp\u003e3.5 Parametric Methods – Mixture of Gaussians 227\u003c\/p\u003e \u003cp\u003e3.6 The Kalman Filter 233\u003c\/p\u003e \u003cp\u003e3.7 Nonparametric Methods 236\u003c\/p\u003e \u003cp\u003e3.7.1 Histogram Based Techniques 236\u003c\/p\u003e \u003cp\u003e3.7.2 Comparing Histograms 239\u003c\/p\u003e \u003cp\u003e3.7.3 IMPLEMENTATION – Multidimensional Histograms 243\u003c\/p\u003e \u003cp\u003e3.7.4 Parzen Method 246\u003c\/p\u003e \u003cp\u003e3.7.4.1 Kernel Based Methods 248\u003c\/p\u003e \u003cp\u003e3.7.4.2 Nearest-Neighbor Method 250\u003c\/p\u003e \u003cp\u003e3.8 The Mean Shift Method 251\u003c\/p\u003e \u003cp\u003e3.8.1 Introduction to the Mean Shift 251\u003c\/p\u003e \u003cp\u003e3.8.2 Continuously Adaptive Mean Shift Method (CamShift) 257\u003c\/p\u003e \u003cp\u003e3.8.3 Algorithmic Aspects of the Mean Shift Tracking 259\u003c\/p\u003e \u003cp\u003e3.8.3.1 Tracking of Multiple Features 259\u003c\/p\u003e \u003cp\u003e3.8.3.2 Tracking of Multiple Objects 260\u003c\/p\u003e \u003cp\u003e3.8.3.3 Fuzzy Approach to the CamShift 261\u003c\/p\u003e \u003cp\u003e3.8.3.4 Discrimination with Background Information 262\u003c\/p\u003e \u003cp\u003e3.8.3.5 Adaptive Update of the Classifiers 263\u003c\/p\u003e \u003cp\u003e3.8.4 IMPLEMENTATION of the CamShift Method 264\u003c\/p\u003e \u003cp\u003e3.9 Neural Networks 267\u003c\/p\u003e \u003cp\u003e3.9.1 Probabilistic Neural Network 267\u003c\/p\u003e \u003cp\u003e3.9.2 IMPLEMENTATION – Probabilistic Neural Network 270\u003c\/p\u003e \u003cp\u003e3.9.3 Hamming Neural Network 274\u003c\/p\u003e \u003cp\u003e3.9.4 IMPLEMENTATION of the Hamming Neural Network 278\u003c\/p\u003e \u003cp\u003e3.9.5 Morphological Neural Network 282\u003c\/p\u003e \u003cp\u003e3.9.5.1 IMPLEMENTATION of the Morphological Neural Network 285\u003c\/p\u003e \u003cp\u003e3.10 Kernels in Vision Pattern Recognition 291\u003c\/p\u003e \u003cp\u003e3.10.1 Kernel Functions 296\u003c\/p\u003e \u003cp\u003e3.10.2 IMPLEMENTATION – Kernels 301\u003c\/p\u003e \u003cp\u003e3.11 Data Clustering 306\u003c\/p\u003e \u003cp\u003e3.11.1 The k-Means Algorithm 308\u003c\/p\u003e \u003cp\u003e3.11.2 Fuzzy c-Means 311\u003c\/p\u003e \u003cp\u003e3.11.3 Kernel Fuzzy c-Means 313\u003c\/p\u003e \u003cp\u003e3.11.4 Measures of Cluster Quality 315\u003c\/p\u003e \u003cp\u003e3.11.5 IMPLEMENTATION Issues 317\u003c\/p\u003e \u003cp\u003e3.12 Support Vector Domain Description 327\u003c\/p\u003e \u003cp\u003e3.12.1 Implementation of Support Vector Machines 333\u003c\/p\u003e \u003cp\u003e3.12.2 Architecture of the Ensemble of One-Class Classifiers 334\u003c\/p\u003e \u003cp\u003e3.13 Appendix – MATLAB R and other Packages for Pattern Classification 336\u003c\/p\u003e \u003cp\u003e3.14 Closure 336\u003c\/p\u003e \u003cp\u003e3.14.1 Chapter Summary 336\u003c\/p\u003e \u003cp\u003e3.14.2 Further Reading 337\u003c\/p\u003e \u003cp\u003eProblems and Exercises 338\u003c\/p\u003e \u003cp\u003eReferences 339\u003c\/p\u003e \u003cp\u003e\u003cb\u003e4 Object Detection and Tracking 346\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e4.1 Introduction 346\u003c\/p\u003e \u003cp\u003e4.2 Direct Pixel Classification 346\u003c\/p\u003e \u003cp\u003e4.2.1 Ground-Truth Data Collection 347\u003c\/p\u003e \u003cp\u003e4.2.2 CASE STUDY – Human Skin Detection 348\u003c\/p\u003e \u003cp\u003e4.2.3 CASE STUDY – Pixel Based Road Signs Detection 352\u003c\/p\u003e \u003cp\u003e4.2.3.1 Fuzzy Approach 353\u003c\/p\u003e \u003cp\u003e4.2.3.2 SVM Based Approach 353\u003c\/p\u003e \u003cp\u003e4.2.4 Pixel Based Image Segmentation with Ensemble of Classifiers 361\u003c\/p\u003e \u003cp\u003e4.3 Detection of Basic Shapes 364\u003c\/p\u003e \u003cp\u003e4.3.1 Detection of Line Segments 366\u003c\/p\u003e \u003cp\u003e4.3.2 UpWrite Detection of Convex Shapes 367\u003c\/p\u003e \u003cp\u003e4.4 Figure Detection 370\u003c\/p\u003e \u003cp\u003e4.4.1 Detection of Regular Shapes from Characteristic Points 371\u003c\/p\u003e \u003cp\u003e4.4.2 Clustering of the Salient Points 375\u003c\/p\u003e \u003cp\u003e4.4.3 Adaptive Window Growing Method 376\u003c\/p\u003e \u003cp\u003e4.4.4 Figure Verification 378\u003c\/p\u003e \u003cp\u003e4.4.5 CASE STUDY – Road Signs Detection System 380\u003c\/p\u003e \u003cp\u003e4.5 CASE STUDY – Road Signs Tracking and Recognition 385\u003c\/p\u003e \u003cp\u003e4.6 CASE STUDY – Framework for Object Tracking 389\u003c\/p\u003e \u003cp\u003e4.7 Pedestrian Detection 395\u003c\/p\u003e \u003cp\u003e4.8 Closure 402\u003c\/p\u003e \u003cp\u003e4.8.1 Chapter Summary 402\u003c\/p\u003e \u003cp\u003e4.8.2 Further Reading 402\u003c\/p\u003e \u003cp\u003eProblems and Exercises 403\u003c\/p\u003e \u003cp\u003eReferences 403\u003c\/p\u003e \u003cp\u003e\u003cb\u003e5 Object Recognition 408\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e5.1 Abstract 408\u003c\/p\u003e \u003cp\u003e5.2 Recognition from Tensor Phase Histograms and Morphological Scale Space 409\u003c\/p\u003e \u003cp\u003e5.2.1 Computation of the Tensor Phase Histograms in Morphological Scale 411\u003c\/p\u003e \u003cp\u003e5.2.2 Matching of the Tensor Phase Histograms 413\u003c\/p\u003e \u003cp\u003e5.2.3 CASE STUDY – Object Recognition with Tensor Phase Histograms in Morphological Scale Space 415\u003c\/p\u003e \u003cp\u003e5.3 Invariant Based Recognition 420\u003c\/p\u003e \u003cp\u003e5.3.1 CASE STUDY – Pictogram Recognition with Affine Moment Invariants 421\u003c\/p\u003e \u003cp\u003e5.4 Template Based Recognition 424\u003c\/p\u003e \u003cp\u003e5.4.1 Template Matching for Road Signs Recognition 425\u003c\/p\u003e \u003cp\u003e5.4.2 Special Distances for Template Matching 428\u003c\/p\u003e \u003cp\u003e5.4.3 Recognition with the Log-Polar and Scale-Spaces 429\u003c\/p\u003e \u003cp\u003e5.5 Recognition from Deformable Models 436\u003c\/p\u003e \u003cp\u003e5.6 Ensembles of Classifiers 438\u003c\/p\u003e \u003cp\u003e5.7 CASE STUDY – Ensemble of Classifiers for Road Sign Recognition from Deformed Prototypes 440\u003c\/p\u003e \u003cp\u003e5.7.1 Architecture of the Road Signs Recognition System 442\u003c\/p\u003e \u003cp\u003e5.7.2 Module for Recognition of Warning Signs 446\u003c\/p\u003e \u003cp\u003e5.7.3 The Arbitration Unit 452\u003c\/p\u003e \u003cp\u003e5.8 Recognition Based on Tensor Decompositions 453\u003c\/p\u003e \u003cp\u003e5.8.1 Pattern Recognition in SubSpaces Spanned by the HOSVD Decomposition of Pattern Tensors 453\u003c\/p\u003e \u003cp\u003e5.8.2 CASE STUDY – Road Sign Recognition System Based on Decomposition of Tensors with Deformable Pattern Prototypes 455\u003c\/p\u003e \u003cp\u003e5.8.3 CASE STUDY – Handwritten Digit Recognition with Tensor Decomposition Method 462\u003c\/p\u003e \u003cp\u003e5.8.4 IMPLEMENTATION of the Tensor Subspace Classifiers 465\u003c\/p\u003e \u003cp\u003e5.9 Eye Recognition for Driver’s State Monitoring 470\u003c\/p\u003e \u003cp\u003e5.10 Object Category Recognition 476\u003c\/p\u003e \u003cp\u003e5.10.1 Part-Based Object Recognition 476\u003c\/p\u003e \u003cp\u003e5.10.2 Recognition with Bag-of-Visual-Words 477\u003c\/p\u003e \u003cp\u003e5.11 Closure 480\u003c\/p\u003e \u003cp\u003e5.11.1 Chapter Summary 480\u003c\/p\u003e \u003cp\u003e5.11.2 Further Reading 481\u003c\/p\u003e \u003cp\u003eProblems and Exercises 482\u003c\/p\u003e \u003cp\u003eReference 483\u003c\/p\u003e \u003cp\u003eA Appendix 487\u003c\/p\u003e \u003cp\u003eA.1 Abstract 487\u003c\/p\u003e \u003cp\u003eA.2 Morphological Scale-Space 487\u003c\/p\u003e \u003cp\u003eA.3 Morphological Tensor Operators 490\u003c\/p\u003e \u003cp\u003eA.4 Geometry of Quadratic Forms 491\u003c\/p\u003e \u003cp\u003eA.5 Testing Classifiers 492\u003c\/p\u003e \u003cp\u003eA.5.1 Implementation of the Confusion Matrix and Testing Object Detection in Images 496\u003c\/p\u003e \u003cp\u003eA.6 Code Acceleration with OpenMP 499\u003c\/p\u003e \u003cp\u003eA.6.1 Recipes for Object-Oriented Code Design with OpenMP 501\u003c\/p\u003e \u003cp\u003eA.6.2 Hints on Using and Code Porting to OpenMP 507\u003c\/p\u003e \u003cp\u003eA.6.3 Performance Analysis 511\u003c\/p\u003e \u003cp\u003eA.7 Useful MATLAB R Functions for Matrix and Tensor Processing 512\u003c\/p\u003e \u003cp\u003eA.8 Short Guide to the Attached Software 513\u003c\/p\u003e \u003cp\u003eA.9 Closure 516\u003c\/p\u003e \u003cp\u003eA.9.1 Chapter Summary 516\u003c\/p\u003e \u003cp\u003eA.9.2 Further Reading 519\u003c\/p\u003e \u003cp\u003eProblems and Exercises 520\u003c\/p\u003e \u003cp\u003eReferences 520\u003c\/p\u003e \u003cp\u003eIndex 523\u003c\/p\u003e\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003eSubject Areas: Electronics \u0026amp; communications engineering [\u003ca title=\"See our other books on Electronics \u0026amp; communications engineering\" href=\"https:\/\/freshlyprintedbooks.co.uk\/search?q=%22Electronics%20\u0026amp;%20communications%20engineering%20%5BTJ%5D%22\"\u003eTJ\u003c\/a\u003e]\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\r\n\u003c\/font\u003e","brand":"Wiley","offers":[{"title":"Brand New","offer_id":52278163341592,"sku":"9780470976371","price":89.99,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0730\/2037\/5320\/files\/9780470976371.jpg?v=1781458736","url":"https:\/\/freshlyprintedbooks.co.uk\/products\/object-detection-and-recognition-in-digital-images-theory-and-practice-hardback-9780470976371","provider":"Freshly Printed Books","version":"1.0","type":"link"}