book

Learning OpenCV 3

by Adrian Kaehler, Gary Bradski

December 2016

Beginner to intermediate

1024 pages

29h 50m

English

O'Reilly Media, Inc.

Read now

Unlock full access

Preface
Purpose of This BookWho This Book Is ForWhat This Book Is NotAbout the Programs in This BookPrerequisitesHow This Book Is Best UsedConventions Used in This BookUsing Code ExamplesO’Reilly Online LearningWe’d Like to Hear from YouAcknowledgmentsThanks for Help on OpenCVThanks for Help on This BookAdrian Adds...Gary Adds...
1. Overview
What Is OpenCV?Who Uses OpenCV?What Is Computer Vision?The Origin of OpenCVOpenCV Block DiagramSpeeding Up OpenCV with IPPWho Owns OpenCV?Downloading and Installing OpenCVInstallationGetting the Latest OpenCV via GitMore OpenCV DocumentationSupplied DocumentationOnline Documentation and the WikiOpenCV Contribution RepositoryDownloading and Building Contributed ModulesPortabilitySummaryExercises
2. Introduction to OpenCV
Include FilesResourcesFirst Program—Display a PictureSecond Program—VideoMoving AroundA Simple TransformationA Not-So-Simple TransformationInput from a CameraWriting to an AVI FileSummaryExercises
3. Getting to Know OpenCV Data Types
The BasicsOpenCV Data TypesOverview of the Basic TypesBasic Types: Getting Down to DetailsHelper ObjectsUtility FunctionsThe Template StructuresSummaryExercises
4. Images and Large Array Types
Dynamic and Variable StorageThe cv::Mat Class: N-Dimensional Dense ArraysCreating an ArrayAccessing Array Elements IndividuallyThe N-ary Array Iterator: NAryMatIteratorAccessing Array Elements by BlockMatrix Expressions: Algebra and cv::MatSaturation CastingMore Things an Array Can DoThe cv::SparseMat Class: Sparse ArraysAccessing Sparse Array ElementsFunctions Unique to Sparse ArraysTemplate Structures for Large Array TypesSummaryExercises
5. Array Operations
More Things You Can Do with Arrayscv::abs()cv::absdiff()cv::add()cv::addWeighted()cv::bitwise_and()cv::bitwise_not()cv::bitwise_or()cv::bitwise_xor()cv::calcCovarMatrix()cv::cartToPolar()cv::checkRange()cv::compare()cv::completeSymm()cv::convertScaleAbs()cv::countNonZero()cv::cvarrToMat()cv::dct()cv::dft()cv::cvtColor()cv::determinant()cv::divide()cv::eigen()cv::exp()cv::extractImageCOI()cv::flip()cv::gemm()cv::getConvertElem() and cv::getConvertScaleElem()cv::idct()cv::idft()cv::inRange()cv::insertImageCOI()cv::invert()cv::log()cv::LUT()cv::magnitude()cv::Mahalanobis()cv::max()cv::mean()cv::meanStdDev()cv::merge()cv::min()cv::minMaxIdx()cv::minMaxLoc()cv::mixChannels()cv::mulSpectrums()cv::multiply()cv::mulTransposed()cv::norm()cv::normalize()cv::perspectiveTransform()cv::phase()cv::polarToCart()cv::pow()cv::randu()cv::randn()cv::randShuffle()cv::reduce()cv::repeat()cv::scaleAdd()cv::setIdentity()cv::solve()cv::solveCubic()cv::solvePoly()cv::sort()cv::sortIdx()cv::split()cv::sqrt()cv::subtract()cv::sum()cv::trace()cv::transform()cv::transpose()SummaryExercises
6. Drawing and Annotating
Drawing ThingsLine Art and Filled PolygonsFonts and TextSummaryExercises
7. Functors in OpenCV
Objects That “Do Stuff”Principal Component Analysis (cv::PCA)Singular Value Decomposition (cv::SVD)Random Number Generator (cv::RNG)SummaryExercises
8. Image, Video, and Data Files
HighGUI: Portable Graphics ToolkitWorking with Image FilesLoading and Saving ImagesA Note About CodecsCompression and DecompressionWorking with VideoReading Video with the cv::VideoCapture ObjectWriting Video with the cv::VideoWriter ObjectData PersistenceWriting to a cv::FileStorageReading from a cv::FileStoragecv::FileNodeSummaryExercises
9. Cross-Platform and Native Windows
Working with WindowsHighGUI Native Graphical User InterfaceWorking with the Qt BackendIntegrating OpenCV with Full GUI ToolkitsSummaryExercises

10. Filters and Convolution
OverviewBefore We BeginFilters, Kernels, and ConvolutionBorder Extrapolation and Boundary ConditionsThreshold OperationsOtsu’s AlgorithmAdaptive ThresholdSmoothingSimple Blur and the Box FilterMedian FilterGaussian FilterBilateral FilterDerivatives and GradientsThe Sobel DerivativeScharr FilterThe LaplacianImage MorphologyDilation and ErosionThe General Morphology FunctionOpening and ClosingMorphological GradientTop Hat and Black HatMaking Your Own KernelConvolution with an Arbitrary Linear FilterApplying a General Filter with cv::filter2D()Applying a General Separable Filter with cv::sepFilter2DKernel BuildersSummaryExercises
11. General Image Transforms
OverviewStretch, Shrink, Warp, and RotateUniform ResizeImage PyramidsNonuniform MappingsAffine TransformationPerspective TransformationGeneral RemappingsPolar MappingsLogPolarArbitrary MappingsImage RepairInpaintingDenoisingHistogram Equalizationcv::equalizeHist(): Contrast equalizationSummaryExercises
12. Image Analysis
OverviewDiscrete Fourier Transformcv::dft(): The Discrete Fourier Transformcv::idft(): The Inverse Discrete Fourier Transformcv::mulSpectrums(): Spectrum MultiplicationConvolution Using Discrete Fourier Transformscv::dct(): The Discrete Cosine Transformcv::idct(): The Inverse Discrete Cosine TransformIntegral Imagescv::integral() for Standard Summation Integralcv::integral() for Squared Summation Integralcv::integral() for Tilted Summation IntegralThe Canny Edge Detectorcv::Canny()Hough TransformsHough Line TransformHough Circle TransformDistance Transformationcv::distanceTransform() for Unlabeled Distance Transformcv::distanceTransform() for Labeled Distance TransformSegmentationFlood FillWatershed AlgorithmGrabcutsMean-Shift SegmentationSummaryExercises
13. Histograms and Templates
Histogram Representation in OpenCVcv::calcHist(): Creating a Histogram from DataBasic Manipulations with HistogramsHistogram NormalizationHistogram ThresholdFinding the Most Populated BinComparing Two HistogramsHistogram Usage ExamplesSome More Sophisticated Histograms MethodsEarth Mover’s DistanceBack ProjectionTemplate MatchingSquare Difference Matching Method (cv::TM_SQDIFF)Normalized Square Difference Matching Method (cv::TM_SQDIFF_NORMED)Correlation Matching Methods (cv::TM_CCORR)Normalized Cross-Correlation Matching Method (cv::TM_CCORR_NORMED)Correlation Coefficient Matching Methods (cv::TM_CCOEFF)Normalized Correlation Coefficient Matching Method (cv::TM_CCOEFF_NORMED)SummaryExercises
14. Contours
Contour FindingContour HierarchiesDrawing ContoursA Contour ExampleAnother Contour ExampleFast Connected Component AnalysisMore to Do with ContoursPolygon ApproximationsGeometry and Summary CharacteristicsGeometrical TestsMatching Contours and ImagesMomentsMore About MomentsMatching and Hu MomentsUsing Shape Context to Compare ShapesSummaryExercises
15. Background Subtraction
Overview of Background SubtractionWeaknesses of Background SubtractionScene ModelingA Slice of PixelsFrame DifferencingAveraging Background MethodAccumulating Means, Variances, and CovariancesA More Advanced Background Subtraction MethodStructuresLearning the BackgroundLearning with Moving Foreground ObjectsBackground Differencing: Finding Foreground ObjectsUsing the Codebook Background ModelA Few More Thoughts on Codebook ModelsConnected Components for Foreground CleanupA Quick TestComparing Two Background MethodsOpenCV Background Subtraction EncapsulationThe cv::BackgroundSubtractor Base ClassKaewTraKuPong and Bowden MethodZivkovic MethodSummaryExercises
16. Keypoints and Descriptors
Keypoints and the Basics of TrackingCorner FindingIntroduction to Optical FlowLucas-Kanade Method for Sparse Optical FlowGeneralized Keypoints and DescriptorsOptical Flow, Tracking, and RecognitionHow OpenCV Handles Keypoints and Descriptors, the General CaseCore Keypoint Detection MethodsKeypoint FilteringMatching MethodsDisplaying ResultsSummaryExercises
17. Tracking
Concepts in TrackingDense Optical FlowThe Farnebäck Polynomial Expansion AlgorithmThe Dual TV-L1 AlgorithmThe Simple Flow AlgorithmMean-Shift and Camshift TrackingMean-ShiftCamshiftMotion TemplatesEstimatorsThe Kalman FilterA Brief Note on the Extended Kalman FilterSummaryExercises
18. Camera Models and Calibration
Camera ModelThe Basics of Projective GeometryRodrigues TransformLens DistortionsCalibrationRotation Matrix and Translation VectorCalibration BoardsHomographyCamera CalibrationUndistortionUndistortion MapsConverting Undistortion Maps Between Representations with cv::convertMaps()Computing Undistortion Maps with cv::initUndistortRectifyMap()Undistorting an Image with cv::remap()Undistortion with cv::undistort()Sparse Undistortion with cv::undistortPoints()Putting Calibration All TogetherSummaryExercises
19. Projection and Three-Dimensional Vision
ProjectionsAffine and Perspective TransformationsBird’s-Eye-View Transform ExampleThree-Dimensional Pose EstimationPose Estimation from a Single CameraStereo ImagingTriangulationEpipolar GeometryThe Essential and Fundamental MatricesComputing Epipolar LinesStereo CalibrationStereo RectificationStereo CorrespondenceStereo Calibration, Rectification, and Correspondence Code ExampleDepth Maps from Three-Dimensional ReprojectionStructure from MotionFitting Lines in Two and Three DimensionsSummaryExercises
20. The Basics of Machine Learning in OpenCV
What Is Machine Learning?Training and Test SetsSupervised and Unsupervised LearningGenerative and Discriminative ModelsOpenCV ML AlgorithmsUsing Machine Learning in VisionVariable ImportanceDiagnosing Machine Learning ProblemsLegacy Routines in the ML LibraryK-MeansMahalanobis DistanceSummaryExercises
21. StatModel: The Standard Model for Learning in OpenCV
Common Routines in the ML LibraryTraining and the cv::ml::TrainData StructurePredictionMachine Learning Algorithms Using cv::StatModelNaïve/Normal Bayes ClassifierBinary Decision TreesBoostingRandom TreesExpectation MaximizationK-Nearest NeighborsMultilayer PerceptronSupport Vector MachineSummaryExercises
22. Object Detection
Tree-Based Object Detection TechniquesCascade ClassifiersSupervised Learning and Boosting TheoryLearning New ObjectsObject Detection Using Support Vector MachinesLatent SVM for Object DetectionThe Bag of Words Algorithm and Semantic CategorizationSummaryExercises
23. Future of OpenCV
Past and PresentOpenCV 3.xHow Well Did Our Predictions Go Last Time?Future FunctionsCurrent GSoC WorkCommunity ContributionsOpenCV.orgSome AI SpeculationAfterword
A. Planar Subdivisions
Delaunay Triangulation, Voronoi TesselationCreating a Delaunay or Voronoi SubdivisionNavigating Delaunay SubdivisionsUsage ExamplesExercises
B. opencv_contrib
An Overview of the opencv_contrib ModulesContents of opencv_contrib
C. Calibration Patterns
Calibration Patterns Used by OpenCV
Bibliography
Index

Content preview from Learning OpenCV 3

Chapter 13. Histograms and Templates

In the course of analyzing images, objects, and video information, we frequently want to represent what we are looking at as a histogram. Histograms can be used to represent such diverse things as the color distribution of an object, an edge gradient template of an object [Freeman95], or the distribution of probabilities representing our current hypothesis about an object’s location. Figure 13-1 shows the use of histograms for rapid gesture recognition. Edge gradients were collected from “up,” “right,” “left,” “stop,” and “OK” hand gestures. A webcam was then set up to watch a person who used these gestures to control web videos. In each frame, color interest regions were detected from the incoming video; then edge gradient directions were computed around these interest regions, and these directions were collected into orientation bins within a histogram. The histograms were then matched against the gesture models to recognize the gesture. The vertical bars in Figure 13-1 show the match levels of the different gestures. The gray horizontal line represents the threshold for acceptance of the “winning” vertical bar corresponding to a gesture model.

Histograms ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Publisher Resources

ISBN: 9781491937983Errata Page

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Learning OpenCV 3

by Adrian Kaehler, Gary Bradski

Chapter 13. Histograms and Templates

Figure 13-1. Local histograms of gradient orientations are used to find the hand and its gesture; here the “winning” gesture (longest vertical bar) is a correct recognition of “L” (move left)

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.