{"product_id":"algorithms-for-image-processing-and-computer-vision-isbn-9780470643853","title":"Algorithms for Image Processing and Computer Vision","description":"\u003cb\u003eA cookbook of algorithms for common image processing applications\u003c\/b\u003e  \u003cp\u003eThanks to advances in computer hardware and software, algorithms have been developed that support sophisticated image processing without requiring an extensive background in mathematics. This bestselling book has been fully updated with the newest of these, including 2D vision methods in content-based searches and the use of graphics cards as image processing computational aids. It’s an ideal reference for software engineers and developers, advanced programmers, graphics programmers, scientists, and other specialists who require highly specialized image processing.\u003c\/p\u003e \u003cul\u003e \u003cli\u003eAlgorithms now exist for a wide variety of sophisticated image processing applications required by software engineers and developers, advanced programmers, graphics programmers, scientists, and related specialists\u003c\/li\u003e \u003cli\u003eThis bestselling book has been completely updated to include the latest algorithms, including 2D vision methods in content-based searches, details on modern classifier methods, and graphics cards used as image processing computational aids\u003c\/li\u003e \u003cli\u003eSaves hours of mathematical calculating by using distributed processing and GPU programming, and gives non-mathematicians the shortcuts needed to program relatively sophisticated applications.\u003c\/li\u003e \u003c\/ul\u003e \u003cp\u003e\u003ci\u003eAlgorithms for Image Processing and Computer Vision, 2nd Edition\u003c\/i\u003e provides the tools to speed development of image processing applications.\u003c\/p\u003e \u003cp\u003ePreface xxi\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 1 Practical Aspects of a Vision System — Image Display, Input\/Output, and Library Calls 1\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eOpenCV 2\u003c\/p\u003e \u003cp\u003eThe Basic OpenCV Code 2\u003c\/p\u003e \u003cp\u003eThe IplImage Data Structure 3\u003c\/p\u003e \u003cp\u003eReading and Writing Images 6\u003c\/p\u003e \u003cp\u003eImage Display 7\u003c\/p\u003e \u003cp\u003eAn Example 7\u003c\/p\u003e \u003cp\u003eImage Capture 10\u003c\/p\u003e \u003cp\u003eInterfacing with the AIPCV Library 14\u003c\/p\u003e \u003cp\u003eWebsite Files 18\u003c\/p\u003e \u003cp\u003eReferences 18\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 2 Edge-Detection Techniques 21\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eThe Purpose of Edge Detection 21\u003c\/p\u003e \u003cp\u003eTraditional Approaches and Theory 23\u003c\/p\u003e \u003cp\u003eModels of Edges 24\u003c\/p\u003e \u003cp\u003eNoise 26\u003c\/p\u003e \u003cp\u003eDerivative Operators 30\u003c\/p\u003e \u003cp\u003eTemplate-Based Edge Detection 36\u003c\/p\u003e \u003cp\u003eEdge Models: The Marr-Hildreth Edge Detector 39\u003c\/p\u003e \u003cp\u003eThe Canny Edge Detector 42\u003c\/p\u003e \u003cp\u003eThe Shen-Castan (ISEF) Edge Detector 48\u003c\/p\u003e \u003cp\u003eA Comparison of Two Optimal Edge Detectors 51\u003c\/p\u003e \u003cp\u003eColor Edges 53\u003c\/p\u003e \u003cp\u003eSource Code for the Marr-Hildreth Edge Detector 58\u003c\/p\u003e \u003cp\u003eSource Code for the Canny Edge Detector 62\u003c\/p\u003e \u003cp\u003eSource Code for the Shen-Castan Edge Detector 70\u003c\/p\u003e \u003cp\u003eWebsite Files 80\u003c\/p\u003e \u003cp\u003eReferences 82\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 3 Digital Morphology 85\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eMorphology Defined 85\u003c\/p\u003e \u003cp\u003eConnectedness 86\u003c\/p\u003e \u003cp\u003eElements of Digital Morphology — Binary Operations 87\u003c\/p\u003e \u003cp\u003eBinary Dilation 88\u003c\/p\u003e \u003cp\u003eImplementing Binary Dilation 92\u003c\/p\u003e \u003cp\u003eBinary Erosion 94\u003c\/p\u003e \u003cp\u003eImplementation of Binary Erosion 100\u003c\/p\u003e \u003cp\u003eOpening and Closing 101\u003c\/p\u003e \u003cp\u003eMAX — A High-Level Programming Language for Morphology 107\u003c\/p\u003e \u003cp\u003eThe ‘‘Hit-and-Miss’’ Transform 113\u003c\/p\u003e \u003cp\u003eIdentifying Region Boundaries 116\u003c\/p\u003e \u003cp\u003eConditional Dilation 116\u003c\/p\u003e \u003cp\u003eCounting Regions 119\u003c\/p\u003e \u003cp\u003eGrey-Level Morphology 121\u003c\/p\u003e \u003cp\u003eOpening and Closing 123\u003c\/p\u003e \u003cp\u003eSmoothing 126\u003c\/p\u003e \u003cp\u003eGradient 128\u003c\/p\u003e \u003cp\u003eSegmentation of Textures 129\u003c\/p\u003e \u003cp\u003eSize Distribution of Objects 130\u003c\/p\u003e \u003cp\u003eColor Morphology 131\u003c\/p\u003e \u003cp\u003eWebsite Files 132\u003c\/p\u003e \u003cp\u003eReferences 135\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 4 Grey-Level Segmentation 137\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eBasics of Grey-Level Segmentation 137\u003c\/p\u003e \u003cp\u003eUsing Edge Pixels 139\u003c\/p\u003e \u003cp\u003eIterative Selection 140\u003c\/p\u003e \u003cp\u003eThe Method of Grey-Level Histograms 141\u003c\/p\u003e \u003cp\u003eUsing Entropy 142\u003c\/p\u003e \u003cp\u003eFuzzy Sets 146\u003c\/p\u003e \u003cp\u003eMinimum Error Thresholding 148\u003c\/p\u003e \u003cp\u003eSample Results From Single Threshold Selection 149\u003c\/p\u003e \u003cp\u003eThe Use of Regional Thresholds 151\u003c\/p\u003e \u003cp\u003eChow and Kaneko 152\u003c\/p\u003e \u003cp\u003eModeling Illumination Using Edges 156\u003c\/p\u003e \u003cp\u003eImplementation and Results 159\u003c\/p\u003e \u003cp\u003eComparisons 160\u003c\/p\u003e \u003cp\u003eRelaxation Methods 161\u003c\/p\u003e \u003cp\u003eMoving Averages 167\u003c\/p\u003e \u003cp\u003eCluster-Based Thresholds 170\u003c\/p\u003e \u003cp\u003eMultiple Thresholds 171\u003c\/p\u003e \u003cp\u003eWebsite Files 172\u003c\/p\u003e \u003cp\u003eReferences 173\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 5 Texture and Color 177\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eTexture and Segmentation 177\u003c\/p\u003e \u003cp\u003eA Simple Analysis of Texture in Grey-Level Images 179\u003c\/p\u003e \u003cp\u003eGrey-Level Co-Occurrence 182\u003c\/p\u003e \u003cp\u003eMaximum Probability 185\u003c\/p\u003e \u003cp\u003eMoments 185\u003c\/p\u003e \u003cp\u003eContrast 185\u003c\/p\u003e \u003cp\u003eHomogeneity 185\u003c\/p\u003e \u003cp\u003eEntropy 186\u003c\/p\u003e \u003cp\u003eResults from the GLCM Descriptors 186\u003c\/p\u003e \u003cp\u003eSpeeding Up the Texture Operators 186\u003c\/p\u003e \u003cp\u003eEdges and Texture 188\u003c\/p\u003e \u003cp\u003eEnergy and Texture 191\u003c\/p\u003e \u003cp\u003eSurfaces and Texture 193\u003c\/p\u003e \u003cp\u003eVector Dispersion 193\u003c\/p\u003e \u003cp\u003eSurface Curvature 195\u003c\/p\u003e \u003cp\u003eFractal Dimension 198\u003c\/p\u003e \u003cp\u003eColor Segmentation 201\u003c\/p\u003e \u003cp\u003eColor Textures 205\u003c\/p\u003e \u003cp\u003eWebsite Files 205\u003c\/p\u003e \u003cp\u003eReferences 206\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 6 Thinning 209\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eWhat Is a Skeleton? 209\u003c\/p\u003e \u003cp\u003eThe Medial Axis Transform 210\u003c\/p\u003e \u003cp\u003eIterative Morphological Methods 212\u003c\/p\u003e \u003cp\u003eThe Use of Contours 221\u003c\/p\u003e \u003cp\u003eChoi\/Lam\/Siu Algorithm 224\u003c\/p\u003e \u003cp\u003eTreating the Object as a Polygon 226\u003c\/p\u003e \u003cp\u003eTriangulation Methods 227\u003c\/p\u003e \u003cp\u003eForce-Based Thinning 228\u003c\/p\u003e \u003cp\u003eDefinitions 229\u003c\/p\u003e \u003cp\u003eUse of a Force Field 230\u003c\/p\u003e \u003cp\u003eSubpixel Skeletons 234\u003c\/p\u003e \u003cp\u003eSource Code for Zhang-Suen\/Stentiford\/Holt Combined Algorithm 235\u003c\/p\u003e \u003cp\u003eWebsite Files 246\u003c\/p\u003e \u003cp\u003eReferences 247\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 7 Image Restoration 251\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eImage Degradations — The Real World 251\u003c\/p\u003e \u003cp\u003eThe Frequency Domain 253\u003c\/p\u003e \u003cp\u003eThe Fourier Transform 254\u003c\/p\u003e \u003cp\u003eThe Fast Fourier Transform 256\u003c\/p\u003e \u003cp\u003eThe Inverse Fourier Transform 260\u003c\/p\u003e \u003cp\u003eTwo-Dimensional Fourier Transforms 260\u003c\/p\u003e \u003cp\u003eFourier Transforms in OpenCV 262\u003c\/p\u003e \u003cp\u003eCreating Artificial Blur 264\u003c\/p\u003e \u003cp\u003eThe Inverse Filter 270\u003c\/p\u003e \u003cp\u003eThe Wiener Filter 271\u003c\/p\u003e \u003cp\u003eStructured Noise 273\u003c\/p\u003e \u003cp\u003eMotion Blur — A Special Case 276\u003c\/p\u003e \u003cp\u003eThe Homomorphic Filter — Illumination 277\u003c\/p\u003e \u003cp\u003eFrequency Filters in General 278\u003c\/p\u003e \u003cp\u003eIsolating Illumination Effects 280\u003c\/p\u003e \u003cp\u003eWebsite Files 281\u003c\/p\u003e \u003cp\u003eReferences 283\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 8 Classification 285\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eObjects, Patterns, and Statistics 285\u003c\/p\u003e \u003cp\u003eFeatures and Regions 288\u003c\/p\u003e \u003cp\u003eTraining and Testing 292\u003c\/p\u003e \u003cp\u003eVariation: In-Class and Out-Class 295\u003c\/p\u003e \u003cp\u003eMinimum Distance Classifiers 299\u003c\/p\u003e \u003cp\u003eDistance Metrics 300\u003c\/p\u003e \u003cp\u003eDistances Between Features 302\u003c\/p\u003e \u003cp\u003eCross Validation 304\u003c\/p\u003e \u003cp\u003eSupport Vector Machines 306\u003c\/p\u003e \u003cp\u003eMultiple Classifiers — Ensembles 309\u003c\/p\u003e \u003cp\u003eMerging Multiple Methods 309\u003c\/p\u003e \u003cp\u003eMerging Type 1 Responses 310\u003c\/p\u003e \u003cp\u003eEvaluation 311\u003c\/p\u003e \u003cp\u003eConverting Between Response Types 312\u003c\/p\u003e \u003cp\u003eMerging Type 2 Responses 313\u003c\/p\u003e \u003cp\u003eMerging Type 3 Responses 315\u003c\/p\u003e \u003cp\u003eBagging and Boosting 315\u003c\/p\u003e \u003cp\u003eBagging 315\u003c\/p\u003e \u003cp\u003eBoosting 316\u003c\/p\u003e \u003cp\u003eWebsite Files 317\u003c\/p\u003e \u003cp\u003eReferences 318\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 9 Symbol Recognition 321\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eThe Problem 321\u003c\/p\u003e \u003cp\u003eOCR on Simple Perfect Images 322\u003c\/p\u003e \u003cp\u003eOCR on Scanned Images — Segmentation 326\u003c\/p\u003e \u003cp\u003eNoise 327\u003c\/p\u003e \u003cp\u003eIsolating Individual Glyphs 329\u003c\/p\u003e \u003cp\u003eMatching Templates 333\u003c\/p\u003e \u003cp\u003eStatistical Recognition 337\u003c\/p\u003e \u003cp\u003eOCR on Fax Images — Printed Characters 339\u003c\/p\u003e \u003cp\u003eOrientation — Skew Detection 340\u003c\/p\u003e \u003cp\u003eThe Use of Edges 345\u003c\/p\u003e \u003cp\u003eHandprinted Characters 348\u003c\/p\u003e \u003cp\u003eProperties of the Character Outline 349\u003c\/p\u003e \u003cp\u003eConvex Deficiencies 353\u003c\/p\u003e \u003cp\u003eVector Templates 357\u003c\/p\u003e \u003cp\u003eNeural Nets 363\u003c\/p\u003e \u003cp\u003eA Simple Neural Net 364\u003c\/p\u003e \u003cp\u003eA Backpropagation Net for Digit Recognition 368\u003c\/p\u003e \u003cp\u003eThe Use of Multiple Classifiers 372\u003c\/p\u003e \u003cp\u003eMerging Multiple Methods 372\u003c\/p\u003e \u003cp\u003eResults From the Multiple Classifier 375\u003c\/p\u003e \u003cp\u003ePrinted Music Recognition — A Study 375\u003c\/p\u003e \u003cp\u003eStaff Lines 376\u003c\/p\u003e \u003cp\u003eSegmentation 378\u003c\/p\u003e \u003cp\u003eMusic Symbol Recognition 381\u003c\/p\u003e \u003cp\u003eSource Code for Neural Net Recognition System 383\u003c\/p\u003e \u003cp\u003eWebsite Files 390\u003c\/p\u003e \u003cp\u003eReferences 392\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 10 Content-Based Search — Finding Images by Example 395\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eSearching Images 395\u003c\/p\u003e \u003cp\u003eMaintaining Collections of Images 396\u003c\/p\u003e \u003cp\u003eFeatures for Query by Example 399\u003c\/p\u003e \u003cp\u003eColor Image Features 399\u003c\/p\u003e \u003cp\u003eMean Color 400\u003c\/p\u003e \u003cp\u003eColor Quad Tree 400\u003c\/p\u003e \u003cp\u003eHue and Intensity Histograms 401\u003c\/p\u003e \u003cp\u003eComparing Histograms 402\u003c\/p\u003e \u003cp\u003eRequantization 403\u003c\/p\u003e \u003cp\u003eResults from Simple Color Features 404\u003c\/p\u003e \u003cp\u003eOther Color-Based Methods 407\u003c\/p\u003e \u003cp\u003eGrey-Level Image Features 408\u003c\/p\u003e \u003cp\u003eGrey Histograms 409\u003c\/p\u003e \u003cp\u003eGrey Sigma — Moments 409\u003c\/p\u003e \u003cp\u003eEdge Density — Boundaries Between Objects 409\u003c\/p\u003e \u003cp\u003eEdge Direction 410\u003c\/p\u003e \u003cp\u003eBoolean Edge Density 410\u003c\/p\u003e \u003cp\u003eSpatial Considerations 411\u003c\/p\u003e \u003cp\u003eOverall Regions 411\u003c\/p\u003e \u003cp\u003eRectangular Regions 412\u003c\/p\u003e \u003cp\u003eAngular Regions 412\u003c\/p\u003e \u003cp\u003eCircular Regions 414\u003c\/p\u003e \u003cp\u003eHybrid Regions 414\u003c\/p\u003e \u003cp\u003eTest of Spatial Sampling 414\u003c\/p\u003e \u003cp\u003eAdditional Considerations 417\u003c\/p\u003e \u003cp\u003eTexture 418\u003c\/p\u003e \u003cp\u003eObjects, Contours, Boundaries 418\u003c\/p\u003e \u003cp\u003eData Sets 418\u003c\/p\u003e \u003cp\u003eWebsite Files 419\u003c\/p\u003e \u003cp\u003eReferences 420\u003c\/p\u003e \u003cp\u003eSystems 424\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 11 High-Performance Computing for Vision and Image Processing 425\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eParadigms for Multiple-Processor Computation 426\u003c\/p\u003e \u003cp\u003eShared Memory 426\u003c\/p\u003e \u003cp\u003eMessage Passing 427\u003c\/p\u003e \u003cp\u003eExecution Timing 427\u003c\/p\u003e \u003cp\u003eUsing clock() 428\u003c\/p\u003e \u003cp\u003eUsing QueryPerformanceCounter 430\u003c\/p\u003e \u003cp\u003eThe Message-Passing Interface System 432\u003c\/p\u003e \u003cp\u003eInstalling MPI 432\u003c\/p\u003e \u003cp\u003eUsing MPI 433\u003c\/p\u003e \u003cp\u003eInter-Process Communication 434\u003c\/p\u003e \u003cp\u003eRunning MPI Programs 436\u003c\/p\u003e \u003cp\u003eReal Image Computations 437\u003c\/p\u003e \u003cp\u003eUsing a Computer Network — Cluster Computing 440\u003c\/p\u003e \u003cp\u003eA Shared Memory System — Using the PC Graphics Processor 444\u003c\/p\u003e \u003cp\u003eGLSL 444\u003c\/p\u003e \u003cp\u003eOpenGL Fundamentals 445\u003c\/p\u003e \u003cp\u003ePractical Textures in OpenGL 448\u003c\/p\u003e \u003cp\u003eShader Programming Basics 451\u003c\/p\u003e \u003cp\u003eVertex and Fragment Shaders 452\u003c\/p\u003e \u003cp\u003eRequired GLSL Initializations 453\u003c\/p\u003e \u003cp\u003eReading and Converting the Image 454\u003c\/p\u003e \u003cp\u003ePassing Parameters to Shader Programs 456\u003c\/p\u003e \u003cp\u003ePutting It All Together 457\u003c\/p\u003e \u003cp\u003eSpeedup Using the GPU 459\u003c\/p\u003e \u003cp\u003eDeveloping and Testing Shader Code 459\u003c\/p\u003e \u003cp\u003eFinding the Needed Software 460\u003c\/p\u003e \u003cp\u003eWebsite Files 461\u003c\/p\u003e \u003cp\u003eReferences 461\u003c\/p\u003e \u003cp\u003eIndex 465\u003c\/p\u003e \u003cb\u003eJ. R. Parker\u003c\/b\u003e is a full professor working in the Art department at the University of Calgary. His major research projects include live performance in online virtual spaces, the design and construction of kinetic games, and the portrayal of Canadian history and culture in digital and online form.  \u003cb\u003eNow — the hottest algorithms for specialized image processing are right in your hands\u003c\/b\u003e  \u003cp\u003eWith this accessible cookbook of algorithms, you'll gain access to the most wanted image-processing applications, including morphology, image restoration, and symbol recognition. Throughout these pages, you'll find real-life examples that clearly describe the latest techniques, saving you hours of lengthy mathematical calculations. And all code is also included on the website, so you can experiment with your own ideas and algorithms for organizing and searching image data sets.\u003c\/p\u003e \u003cp\u003eThis updated edition provides practical solutions so you can:\u003c\/p\u003e \u003cul\u003e \u003cli\u003e \u003cp\u003eProgram state-of-the-art image-processing capabilities into software\u003c\/p\u003e \u003c\/li\u003e \u003cli\u003e \u003cp\u003eFind the steps for taking advantage of classifiers\u003c\/p\u003e \u003c\/li\u003e \u003cli\u003e \u003cp\u003eApply 2D vision methods in content-based searches\u003c\/p\u003e \u003c\/li\u003e \u003cli\u003e \u003cp\u003ePerform edge detection, thinning, thresholding, and morphology\u003c\/p\u003e \u003c\/li\u003e \u003cli\u003e \u003cp\u003eLink all the computers on your network into a large image-processing cluster\u003c\/p\u003e \u003c\/li\u003e \u003cli\u003e \u003cp\u003eProgram the GPU to do image-processing and vision tasks\u003c\/p\u003e \u003c\/li\u003e \u003cli\u003e \u003cp\u003eSelect the best method for searching through images\u003c\/p\u003e \u003c\/li\u003e \u003c\/ul\u003e \u003cp\u003eVisit the companion website at www.wiley.com\/go\/jrparker to access all code used in this book.\u003c\/p\u003e","brand":"Wiley","offers":[{"title":"Default Title","offer_id":47988713619685,"sku":"NP9780470643853","price":100.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1842\/7735\/files\/9780470643853.jpg?v=1761781297","url":"https:\/\/k12savings.com\/products\/algorithms-for-image-processing-and-computer-vision-isbn-9780470643853","provider":"K12savings","version":"1.0","type":"link"}