Index
A
- active appearance model (AAM) / Active appearance models and constrained local models
- affine transform / Affine constraint
- algorithm options, OpenCV / Algorithm options in OpenCV
- alien mode generation, with skin detection
- skin detection algorithm / Skin detection algorithm
- face outline, drawing / Showing the user where to put their face
- alpha channel / Common pitfalls and suggested solutions
- analysis of variance (ANOVA) / Example comparative performance test of algorithms
- anchoring / Common pitfalls and suggested solutions
- ANPR algorithm / ANPR algorithm
- AOI application
- creating / Creating an application for AOI
- input parameters / Creating an application for AOI
- ARGB / Common pitfalls and suggested solutions
- ARM NEON SIMD optimizations / Installing OpenCV on an embedded device
- artificial neural network / Plate recognition
- artificial neural networks (ANN) / Introducing machine learning concepts
- ArUco
- camera, calibrating with / Camera calibration with ArUco
- Augmented reality (AR)
- about / Augmented reality and pose estimation
- camera calibration / Camera calibration
- markers, for planar reconstruction / Augmented reality markers for planar reconstruction
- Augmentor
- URL / Preparing the data
- about / Preparing the data
- Automatic License Plate Recognition (ALPR) / Introduction to ANPR
- Automatic Number Plate Recognition (ANPR) / Introduction to ANPR
- automatic object inspection classification example
- about / Automatic object inspection classification example
- feature extraction / Feature extraction
- SVM model, training / Training an SVM model
- input image prediction / Input image prediction
- Automatic Vehicle Identification (AVI) / Introduction to ANPR
B
- background subtraction / Understanding background subtraction
- backpropagation / What is a neural network and how can we learn from data?
- BaseOCR virtual class / Text recognition
- basic CMake configuration file / Basic CMake configuration file
- Bayes classifier / Machine learning
- BGR image format / Images and matrices
- BGR order / Common pitfalls and suggested solutions
- Binarization image / Isolating objects in a scene
- Black Hat transform
- about / Black Hat transform
- performing / Black Hat transform
- Blender 3D
- blobFromImage function
- parameters / Importing YOLO into OpenCV
- Boost Graph Library (BGL) / Finding feature tracks
- bucket tool / Text extraction
- bundle adjustment / Bundle Adjustment
C
- C++11 / History of OpenCV from v1 to v4
- C++11 version / Generating a CMake script file
- C++ API / History of OpenCV from v1 to v4
- C++ Archive Network (CPPAN) / Installing Tesseract on Windows
- Caffe / Deep learning
- California Institute of Technology (CalTech) / OpenCV and the data revolution in computer vision
- camera
- power draw / Power draw of Cartoonifier running on desktop versus embedded system
- technical requisites / Technical requirements
- calibrating / Camera calibration
- access, in Android OS / Camera access in Android OS
- finding / Finding and opening the camera
- opening / Finding and opening the camera
- calibrating, with ArUco / Camera calibration with ArUco
- orthographic camera / Augmented reality with jMonkeyEngine
- camera calibration / Core concepts of SfM, Calibrated cameras and epipolar geometry
- camera intrinsic parameters matrix / Camera calibration
- camera resectioning / Core concepts of SfM
- cameras
- reading / Reading videos and cameras
- Carnegie Mellon (CMU) Robotics Institute / OpenCV and the data revolution in computer vision
- car plate recognition (CPR) / Introduction to ANPR
- Cartoonifier power / Power draw of Cartoonifier running on desktop versus embedded system
- cartoonize effect / Cartoonize effect
- CIELab color space / Skin detection algorithm
- classification / Classification
- CLM methods / Theory and context
- CMake
- configuration file / Basic CMake configuration file
- library, creating / Creating a library
- dependencies, managing / Managing dependencies
- complex script, creating / Making the script more complex
- CMake's CTest
- CMake build system / History of OpenCV from v1 to v4
- CMake script file
- generating / Generating a CMake script file
- CMakeTest / Basic CMake configuration file
- CNN layer structure / Creating a TensorFlow model
- CocoaPods
- used, for setting up iOS OpenCV project / Setting up an iOS OpenCV project with CocoaPods
- COCO dataset / The YOLO dataset, vocabulary, and model
- color filtering / Cartoonize effect
- common pitfalls, OpenCV
- about / Common pitfalls and suggested solutions
- solutions / Common pitfalls and suggested solutions
- complex script
- creating / Making the script more complex
- computational photography / Computational photography
- Computer Science and Artificial Intelligence Lab (CSAIL) / OpenCV and the data revolution in computer vision
- computer vision
- topics, with level of offering / Is it covered in OpenCV?
- problems / Which algorithm is best?
- computer vision algorithms
- about / Which algorithm is best?
- computation resources / Which algorithm is best?
- data / Which algorithm is best?
- performance requirements / Which algorithm is best?
- meta-algorithmic / Which algorithm is best?
- computer vision and pattern recognition (CVPR) / How the text API works
- computer vision applications, with machine learning
- basic structure / Computer vision and the machine learning workflow
- workflow / Computer vision and the machine learning workflow
- Pre-process / Computer vision and the machine learning workflow
- Segmentation / Computer vision and the machine learning workflow
- Feature Extraction / Computer vision and the machine learning workflow
- Classification result / Computer vision and the machine learning workflow
- Post-process / Computer vision and the machine learning workflow
- connected component algorithm
- about / The connected components algorithm
- connectedComponents function / The connected components algorithm
- connectedComponentsWithStats function / The connected components algorithm
- connectedComponents function
- image / The connected components algorithm
- labels / The connected components algorithm
- connectivity / The connected components algorithm
- type / The connected components algorithm
- connectedComponentsWithStats function
- constrained local model (CLM) methods / Theory and context, Active appearance models and constrained local models
- continuously-adaptive meanshift (CAMShift) / Building an interactive object tracker
- convolutional layer / Convolutional neural networks
- convolutional neural network / Convolutional neural networks
- Convolutional Neural Network (CNN) / Deep learning
- convolutional neural network, with TensorFlow
- creating / Creating and training a convolutional neural network with TensorFlow
- training / Creating and training a convolutional neural network with TensorFlow
- data, preparing / Preparing the data
- TensorFlow model, creating / Creating a TensorFlow model
- model, preparing for OpenCV / Preparing a model for OpenCV
- model, importing in OpenCV C++ code / Import and use model in OpenCV C++ code
- convolutional neural networks (CNN)
- about / Regression methods, Character classification using a convolutional neural network
- convolutional / Character classification using a convolutional neural network
- pooling / Character classification using a convolutional neural network
- flatten / Character classification using a convolutional neural network
- fully connected / Character classification using a convolutional neural network
- dropout / Character classification using a convolutional neural network
- loss layer / Character classification using a convolutional neural network
- core concepts, structure from motion (SfM)
- calibrated cameras / Calibrated cameras and epipolar geometry
- epipolar geometry / Calibrated cameras and epipolar geometry
- stereo reconstruction / Stereo reconstruction and SfM
- cornerHarris() documentation
- reference link / Detecting points using the Harris corner detector
- CPPAN client
- URL, for downloading / Building the latest library
- cross-compilation / Porting from desktop to an embedded device
D
- 3D reconstruction / 3D reconstruction
- 3D rigid transform / Image feature matching
- data
- data revolution
- in computer vision / OpenCV and the data revolution in computer vision
- decision trees / Machine learning
- deep learning
- about / Deep learning, Introduction to deep learning
- data, learning / What is a neural network and how can we learn from data?
- neural networks (NNs) / What is a neural network and how can we learn from data?
- convolutional neural network / Convolutional neural networks
- in OpenCV / Deep learning in OpenCV
- deep neural networks (DNN) / Convolutional neural networks
- dense reconstruction
- MVS used / MVS for dense reconstruction
- dependencies
- managing / Managing dependencies
- descriptors / Image feature matching
- deskewing / Creating an OCR function
- dilation / Thickening the shapes
- direct linear method / Stereo reconstruction and SfM
- disparity / Stereo reconstruction and SfM
- distance function / Active appearance models and constrained local models
- distortion parameters / Camera calibration
- DLT method / How to check when an algorithm was added to OpenCV
- DotNetNuke (DNN) / Importing YOLO into OpenCV
- drawContours function
- parameters / The findContours algorithm
- dropout layers / Convolutional neural networks
- dynamic link libraries (DLLs) / Windows
E
- edge detection / Cartoonize effect
- Eigenfaces / Training the face recognition system from collected faces
- embedded Cartoonifier system
- customizing / Customizing your embedded system!
- embedded device
- main camera processing loop, porting from desktop / Porting from desktop to an embedded device
- OpenCV installation / Installing OpenCV on an embedded device
- epipolar constraint / Calibrated cameras and epipolar geometry, Image feature matching
- epipolar geometry (EG) / Core concepts of SfM
- epipolar line / Calibrated cameras and epipolar geometry
- epipolar plane / Calibrated cameras and epipolar geometry
- ERFilters / Text detection
- erosion / Slimming the shapes
- essential matrix / Calibrated cameras and epipolar geometry
- example comparative performance test, of algorithms / Example comparative performance test of algorithms
- extractors / Image feature matching
- extremal region (ER) / Text detection
- extrinsic parameters matrix / Calibrated cameras and epipolar geometry
F
- face cascade XML / What happened in the code?
- face detection
- about / Get your sunglasses on, Introduction to face detection and face recognition, Face detection, Detecting the face
- code, viewing / Looking inside the code
- tracking / Tracking the nose, mouth, and ears
- with SSD / Face detection with SSD
- implementing, OpenCV cascade classifiers used / Implementing face detection using OpenCV cascade classifiers
- Haar or LBP detector, loading / Loading a Haar or LBP detector for object or face detection
- webcam, accessing / Accessing the webcam
- object detecting, Haar or LBP classifier used / Detecting an object using the Haar or LBP classifier
- camera image, shrinking / Detecting an object using the Haar or LBP classifier
- implementing, OpenCV deep learning module used / Implementing face detection using the OpenCV deep learning module
- face direction estimation, from landmarks
- about / Estimating face direction from landmarks
- estimated pose calculation / Estimated pose calculation
- pose, projecting on image / Projecting the pose on the image
- face landmark detection
- technical requirements / Technical requirements
- theory / Theory and context
- context / Theory and context
- face landmark detection, in OpenCV
- about / Facial landmark detection in OpenCV
- error, measuring / Measuring error
- face mask
- overlaying, in live video / Overlaying a face mask in a live video
- code, viewing / What happened in the code?
- face preprocessing
- about / Introduction to face detection and face recognition, Face preprocessing
- eye detection / Eye detection
- eye search regions / Eye search regions
- geometrical transformation / Geometrical transformation
- histogram equalization, for left and right sides / Separate histogram equalization for left and right sides
- smoothing / Smoothing
- elliptical mask / Elliptical mask
- face recognition / Face and object recognition
- about / Introduction to face detection and face recognition, Face recognition
- recognizing, people from faces / Face identification – recognizing people from their faces
- face, verifying / Face verification—validating that it is the claimed person
- faces
- collecting / Collecting faces and learning from them
- preprocessed faces, collecting for training / Collecting preprocessed faces for training
- recognition system, training from collected faces / Training the face recognition system from collected faces
- learned knowledge, viewing / Viewing the learned knowledge
- average face / Average face
- Eigenvalues / Eigenvalues, Eigenfaces, and Fisherfaces
- Fisherfaces / Eigenvalues, Eigenfaces, and Fisherfaces
- files, saving / Finishing touches—saving and loading files
- files, loading / Finishing touches—saving and loading files
- interactive GUI, creating / Finishing touches—making a nice and interactive GUI
- GUI elements, drawing / Drawing the GUI elements
- startup mode / Startup mode
- detection mode / Detection mode
- collection mode / Collection mode
- training mode / Training mode
- recognition mode / Recognition mode
- mouse clicks, handling / Checking and handling mouse clicks
- mouse clicks, checking / Checking and handling mouse clicks
- Farneback algorithm / Feature-based tracking, Farneback algorithm
- Fast Approximate Nearest Neighbor Search Library (FLANN) / Machine learning
- feature-based tracking
- about / Feature-based tracking
- Lucas-Kanade method / Lucas-Kanade method
- Farneback algorithm / Farneback algorithm
- feature extraction / Feature extraction
- feature extraction, automatic object inspection classification example / Feature extraction
- feature repeatability / Image feature matching
- Features From Accelerated Segment Test (FAST) / Feature extraction
- feature tracks / Finding feature tracks
- feedforward / Deep learning in OpenCV
- fiducial markers / Augmented reality and pose estimation
- field-of-view (FOV) / Augmented reality with jMonkeyEngine
- FileStorage
- writing to / Writing to FileStorage
- findContours algorithm
- about / The findContours algorithm
- image / The findContours algorithm
- contour / The findContours algorithm
- hierarchy / The findContours algorithm
- mode / The findContours algorithm
- method / The findContours algorithm
- offset / The findContours algorithm
- Fisherfaces / Training the face recognition system from collected faces
- flatten layers / Convolutional neural networks
- focalism cognitive bias / Common pitfalls and suggested solutions
- focal length / Calibrated cameras and epipolar geometry
- frame differencing
- about / Frame differencing
- working / How well does it work?
- frames per seconds (FPS) / Speed comparison of Cartoonifier on desktop versus embedded
- freezing / Preparing a model for OpenCV
- fundamental matrix / Calibrated cameras and epipolar geometry
G
- getRotationMatrix2D OpenCV function
- Google Summer of Code (GSoC) / Technical requirements
- gradient boosting trees (GBT) / Regression methods
- Graph API (G-API) module / History of OpenCV from v1 to v4
- graphical user interface (GUI)
- about / GUI
- with OpenCV / Basic graphical user interface with OpenCV
- slider event, adding / Adding slider and mouse events to our interfaces
- mouse event, adding / Adding slider and mouse events to our interfaces
- with Qt / Graphic user interface with Qt
- buttons, adding / Adding buttons to the user interface
- creating / Creating the graphical user interface
- ground truth / Which algorithm is best?, Example comparative performance test of algorithms
H
- Haar cascades / Understanding Haar cascades
- Haar features / Understanding Haar cascades
- Hamming distance metric / Image feature matching
- Harris corner detector
- used, for detecting points / Detecting points using the Harris corner detector
- features / Good features to track
- hidden layers / What is a neural network and how can we learn from data?
- high dynamic range imaging (HDRI) / Images and matrices
- histogram
- drawing / Drawing a histogram
- parameters / Drawing a histogram
- histogram of gradients (HOG) / Active appearance models and constrained local models
- HMMDecoder / Text recognition
- holistic methods / Theory and context
- Homebrew
- homogeneous coordinates / Calibrated cameras and epipolar geometry
- homography / Augmented reality markers for planar reconstruction, How to check when an algorithm was added to OpenCV
- HSV (Hue, Saturation, Value) / Skin detection algorithm, Common pitfalls and suggested solutions
- hue saturation value (HSV) / Tracking objects of a specific color
- human visual system / Understanding the human visual system
- Human Visual System (HVS) / Understanding the human visual system
- hyperparameter tuning / Common pitfalls and suggested solutions
I
- identify text / Creating an OCR function
- image color equalization / Image color equalization
- image content
- recognizing, by humans / How do humans understand image content?
- difficulties for machines, in image recognition / Why is it difficult for machines to understand image content?
- image feature matching / Image feature matching
- image formation / Core concepts of SfM
- image processing app, porting from desktop to embedded device
- about / Porting from desktop to an embedded device
- equipment setup, for code development / Equipment setup to develop code for an embedded device
- Raspberry Pi, configuring / Configuring a new Raspberry Pi
- OpenCV, installing on embedded device / Installing OpenCV on an embedded device
- Raspberry Pi Camera Module, using / Using the Raspberry Pi Camera Module
- Raspberry Pi Camera Module driver, installing / Installing the Raspberry Pi Camera Module driver
- Cartoonifier, running in fullscreen / Making Cartoonifier run in fullscreen
- mouse cursor, hiding / Hiding the mouse cursor
- Cartoonifier, running automatically after bootup / Running Cartoonifier automatically after bootup
- Cartoonifier speed comparison, on desktop / Speed comparison of Cartoonifier on desktop versus embedded
- camera, changing / Changing the camera and camera resolution
- camera resolution, changing / Changing the camera and camera resolution
- Cartoonifier power draw, running / Power draw of Cartoonifier running on desktop versus embedded system
- image processing operations / Image processing operations
- images
- about / Images and matrices
- matrices / Images and matrices
- reading / Reading/writing images
- writing / Reading/writing images
- imgcodecs module / Inbuilt data structures and input/output
- inbuilt data structures / Inbuilt data structures and input/output
- infrared (IR) camera / Introduction to ANPR
- input image, preprocesssing
- about / Preprocessing the input image
- noise removal / Noise removal
- background, removing with light pattern / Removing the background using the light pattern for segmentation
- thresholding / Thresholding
- input image, segmenting
- about / Segmenting our input image
- connected component algorithm / The connected components algorithm
- findContours algorithm / The findContours algorithm
- integral images / What are integral images?
- Intelligent Behaviour Understanding Group (iBUG) / Technical requirements
- interactive object tracker
- building / Building an interactive object tracker
- intrinsic parameters / Calibrated cameras and epipolar geometry
- intrinsic parameters matrix / Calibrated cameras and epipolar geometry
- iOS OpenCV project
- setting up, CocoaPods used / Setting up an iOS OpenCV project with CocoaPods
- CocoaPods used / Setting up an iOS OpenCV project with CocoaPods
- iOS panoramas
- requisites / Technical requirements
- iOS UI
- for panorama capture / iOS UI for panorama capture
J
- jMonkeyEngine
- augmented reality / Augmented reality with jMonkeyEngine
K
- k-nearest neighbors (KNN) / Machine learning
- Kinect / Surface matching
L
- least median squares (LMedS) / Random sample consensus (RANSAC)
- Levenberg-Marquardt / Camera calibration
- libmv
- library
- creating / Creating a library
- local binary features (LBF) / Regression methods
- lomography effect / Lomography effect
- look-up table (LUT) / Lomography effect
- loss function / Which algorithm is best?
- lower bits / Segmentation
- Lucas-Kanade method / Feature-based tracking, Lucas-Kanade method
- luminosity / Adding buttons to the user interface
M
- machine learning
- concepts / Introducing machine learning concepts
- machine learning algorithms
- about / Machine learning, Introducing machine learning concepts
- supervised learning / Introducing machine learning concepts
- unsupervised learning / Introducing machine learning concepts
- reinforcement learning / Introducing machine learning concepts
- results / Introducing machine learning concepts
- main camera processing loop, for desktop app
- about / Main camera processing loop for a desktop app
- black and white sketch, generating / Generating a black and white sketch
- color painting, generating / Generating a color painting and a cartoon
- cartoon, generating / Generating a color painting and a cartoon
- evil mode, generating with edge filters / Generating an evil mode using edge filters
- alien mode, generating with skin detection / Generating an alien mode using skin detection
- Makefiles / Basic CMake configuration file
- mask image / What happened in the code?
- match graph / Finding feature tracks
- matrices / Images and matrices
- matrix inversion / Basic matrix operations
- matrix operations / Basic matrix operations
- maximally stable extremal regions (MSERs) / Text segmentation, Extremal regions
- Mean Squared Error (MSE) / Example comparative performance test of algorithms
- mid-point method / Stereo reconstruction and SfM
- mixture model / The Mixture of Gaussians approach
- Mixture of Gaussians (MOG) approach
- about / The Mixture of Gaussians approach
- code / What happened in the code?
- MOG2 approach
- morphological closing
- about / Morphological closing
- performing / Morphological closing
- morphological erosion
- performing / Slimming the shapes
- morphological gradient
- performing / Drawing the boundary
- morphological image processing / Morphological image processing
- morphological opening
- about / Morphological opening
- performing / Morphological opening
- morphological operators
- applying / What's the underlying principle?
- about / Other morphological operators
- morphological opening / Morphological opening
- morphological closing / Morphological closing
- morphological gradient / Drawing the boundary
- boundary, drawing / Drawing the boundary
- Top Hat transform / Top Hat transform
- Black Hat transform / Black Hat transform
- MySQL project / History of OpenCV from v1 to v4
N
- naive background subtraction
- about / Naive background subtraction
- process / Naive background subtraction
- working / Does it work well?
- native compilation / Porting from desktop to an embedded device
- natural markers / Augmented reality and pose estimation
- negative samples / Understanding Haar cascades
- neural networks (NNs)
O
- object classification
- technical requisites / Technical requirements
- object detection / Object detection
- object recognition / Face and object recognition
- objects
- isolating, in scene / Isolating objects in a scene
- tracking, of specific color / Tracking objects of a specific color
- object types
- about / Other basic object types
- Vec object type / Vec object type
- Scalar / Scalar object type
- Size object type / Size object type
- Rect / Rect object type
- RotatedRect / RotatedRect object type
- OCRBeamSearchDecoder / Text recognition
- OCRHMMDecoder / Text recognition
- OCR segmentation / OCR segmentation
- OCRTesseract / Text recognition
- OmniVision sensor / Using the Raspberry Pi Camera Module
- only one matching feature / Finding feature tracks
- OpenCV
- about / What can you do with OpenCV?
- inbuilt data structures / Inbuilt data structures and input/output
- input and output, of video files / Inbuilt data structures and input/output
- image processing operations / Image processing operations
- graphical user interface (GUI) / GUI, Basic graphical user interface with OpenCV
- video analysis / Video analysis
- 3D reconstruction / 3D reconstruction
- feature extraction / Feature extraction
- object detection / Object detection
- machine learning algorithms / Machine learning
- computational photography / Computational photography
- shape analysis / Shape analysis
- optical flow algorithms / Optical flow algorithms
- face recognition / Face and object recognition
- object recognition / Face and object recognition
- surface matching / Surface matching
- text detection / Text detection and recognition
- text recognition / Text detection and recognition
- deep learning / Deep learning
- data persistence / Basic data persistence and storage
- data storage / Basic data persistence and storage
- FileStorage, writing to / Writing to FileStorage
- installation, on embedded device / Installing OpenCV on an embedded device
- SfM implementation / Implementing SfM in OpenCV
- facial landmark detection / Facial landmark detection in OpenCV
- stitching, in Objective-C++ wrapper / OpenCV stitching in an Objective-C++ wrapper
- implementations / Is it covered in OpenCV?, Algorithm options in OpenCV
- algorithm options / Algorithm options in OpenCV
- multiple implementations / Algorithm options in OpenCV
- history / History of OpenCV from v1 to v4
- in computer vision / OpenCV and the data revolution in computer vision
- historic algorithms / Historic algorithms in OpenCV
- URL / How to check when an algorithm was added to OpenCV
- common pitfalls / Common pitfalls and suggested solutions
- OpenCV 3.0
- algorithms / Extremal region filtering
- OpenCV algorithm
- technical requisites / Technical requirements
- checking / How to check when an algorithm was added to OpenCV
- OpenCV attic
- OpenCV C++ code
- model, importing in / Import and use model in OpenCV C++ code
- OpenCV change logs
- OpenCV deep learning module
- used, for implementing face detection / Implementing face detection using the OpenCV deep learning module
- OpenCV development
- technical requisites / Technical requirements
- images / Images and matrices
- matrices / Images and matrices
- video and camera reading / Reading videos and cameras
- OpenCV HAL (Hardware Acceleration Layer) / History of OpenCV from v1 to v4
- OpenCV installation
- about / Installing OpenCV
- on Windows / Windows
- on macOS X / Mac OS X
- on Linux / Linux
- OpenCV machine learning algorithms
- about / OpenCV machine learning algorithms
- class hierarchy / OpenCV machine learning algorithms
- OpenCV source repository
- OpenCV user interface / Introducing the OpenCV user interface
- OpenGL support / OpenGL support
- OpenImages V4 / OpenCV and the data revolution in computer vision
- Open Neural Network Exchange (ONNX) / Deep learning in OpenCV
- optical character recognition
- about / Introducing optical character recognition
- text preprocessing and segmentation / Introducing optical character recognition
- optical character recognition (OCR) / Removing the background using the light pattern for segmentation, Introducing machine learning concepts, Introduction to ANPR
- optical flow algorithms / Optical flow algorithms
- optimization / Common pitfalls and suggested solutions
- oriented BRIEF (ORB) / Image feature matching, Feature extraction and robust matching for panoramas
- Otsu method / Historic algorithms in OpenCV
- over-optimization / Common pitfalls and suggested solutions
P
- Panoramic Image Stitching methods
- about / Panoramic image stitching methods
- feature, extraction / Feature extraction and robust matching for panoramas
- robust matching, for panoramas / Feature extraction and robust matching for panoramas
- Affine constraint / Affine constraint
- random sample consensus (RANSAC) / Random sample consensus (RANSAC)
- homography constraint / Homography constraint
- bundle adjustment / Bundle Adjustment
- images, warping for / Warping images for panorama creation
- parallax effect / Stereo reconstruction and SfM
- pepper noise / Reducing the random pepper noise from the sketch image
- Perspective-n-Point (PnP) / Augmented reality markers for planar reconstruction
- perspective divide / Camera calibration
- pinhole camera model / Calibrated cameras and epipolar geometry, Camera calibration
- pixel / Images and matrices
- plate detection
- about / Plate detection
- segmentation / Segmentation
- classification / Classification
- plate recognition
- about / Plate recognition
- OCR segmentation / OCR segmentation
- character classification, with neural network / Character classification using a convolutional neural network
- Point-n-Perspective (PnP) algorithm / Core concepts of SfM, Stereo reconstruction and SfM, Estimated pose calculation, Camera calibration
- Point object type / Point object type
- pooling layers / Convolutional neural networks
- portable USB charger / Porting from desktop to an embedded device
- positive samples / Understanding Haar cascades
- predict function
- about / OpenCV machine learning algorithms
- samples / OpenCV machine learning algorithms
- results / OpenCV machine learning algorithms
- flags / OpenCV machine learning algorithms
- premature optimization / Common pitfalls and suggested solutions
- preprocessing / Preprocessing stage
- preprocessing stage
- about / Preprocessing stage
- image, thresholding / Thresholding the image
- text segmentation / Text segmentation
- preprocessing steps
- Binarization / Isolating objects in a scene
- Noise Removal / Isolating objects in a scene
- Light Removal / Isolating objects in a scene
- principal component analysis (PCA) / Active appearance models and constrained local models, Classification
- principal point / Camera calibration
- Principle Point / Calibrated cameras and epipolar geometry
- pure horizontal translation / Stereo reconstruction and SfM
- PyTorch / History of OpenCV from v1 to v4
R
- random sample consensus (RANSAC) / Random sample consensus (RANSAC), How to check when an algorithm was added to OpenCV
- Raspberry Pi Camera Module driver
- installing / Installing the Raspberry Pi Camera Module driver
- Raspbian IMG / Configuring a new Raspberry Pi
- Raspbian Lite / Configuring a new Raspberry Pi
- reciprocity filter
- implementing / Image feature matching
- reconstruction factorization / Core concepts of SfM
- Rect object type / Rect object type
- region of interest (ROI) / Rect object type, Segmenting our input image, Text extraction
- regression methods / Theory and context, Regression methods
- results category, machine learning algorithm
- classification / Introducing machine learning concepts
- regression / Introducing machine learning concepts
- clustering / Introducing machine learning concepts
- density estimation / Introducing machine learning concepts
- RGB (Red-Green-Blue) / Skin detection algorithm
- RGBA / Common pitfalls and suggested solutions
- RGB image / Text detection
- rigid transformation / Estimated pose calculation
- Robust Feature Matching / Core concepts of SfM
- RotatedRect object type / RotatedRect object type
- Ruby script / Installing Tesseract on Mac
- run function
- input channel / Text detection
- regions / Text detection
S
- Scalar object type / Scalar object type
- Scale Invariant Feature Transform (SIFT) / Feature extraction
- scale invariant feature transform (SIFT) / Feature extraction and robust matching for panoramas
- scanned text
- tridimensionality / The scene detection problem
- variety / The scene detection problem
- illumination and shadows / The scene detection problem
- blurring / The scene detection problem
- segmentation / Segmentation
- segmentation steps
- contour detection / Isolating objects in a scene
- connected components extraction / Isolating objects in a scene
- SfM implementation, in OpenCV
- about / Implementing SfM in OpenCV
- image feature matching / Image feature matching
- feature tracks, finding / Finding feature tracks
- 3D reconstruction / 3D reconstruction and visualization
- 3D visualization / 3D reconstruction and visualization
- MVS, for dense reconstruction / MVS for dense reconstruction
- shape analysis / Shape analysis
- shapes
- slimming / Slimming the shapes
- thickening / Thickening the shapes
- simultaneous localization and mapping (SLAM) / Augmented reality and pose estimation, Panoramic image stitching methods
- Single Shot Detection (SSD)
- used, for face detection / Face detection with SSD
- about / Face detection with SSD
- model architecture / SSD model architecture
- face detection, importing into OpenCV / Importing SSD face detection into OpenCV
- Single Shot Multibox Detector (SSD) / Face detection
- singular value decomposition (SVD) / Calibrated cameras and epipolar geometry
- Size object type / Size object type
- skin color changer
- implementing / Implementation of the skin color changer
- random pepper noise, reducing from sketch image / Reducing the random pepper noise from the sketch image
- softmax layers / Convolutional neural networks
- speeded up robust features (SURF) / Feature extraction and robust matching for panoramas
- Speeded Up Robust Features (SURF) / Feature extraction
- spherical coordinates / Warping images for panorama creation
- static linking
- about / Static linking
- reference link / Static linking
- statistical significance / Example comparative performance test of algorithms
- StatModel class / OpenCV machine learning algorithms
- about / OpenCV machine learning algorithms
- isTrained() / OpenCV machine learning algorithms
- isClassifier() / OpenCV machine learning algorithms
- getVarCount() / OpenCV machine learning algorithms
- calcError() / OpenCV machine learning algorithms
- stereo depth reconstruction / Stereo reconstruction and SfM
- stereo reconstruction / Core concepts of SfM, Stereo reconstruction and SfM
- structure from motion (SfM)
- technical requisites / Technical requirements
- core concepts / Core concepts of SfM
- about / Augmented reality and pose estimation, Panoramic image stitching methods
- structuring element / What's the underlying principle?
- supervised / What is a neural network and how can we learn from data?
- support vector machines (SVM) / Machine learning, Introducing machine learning concepts
- SURF (Speeded Up Robust Features) / Image feature matching
- surface matching / Surface matching
- SVM model, automatic object inspection classification example
- training / Training an SVM model
T
- t-test / Example comparative performance test of algorithms
- Telchin chain approximation algorithm / The findContours algorithm
- TensorFlow / Deep learning, History of OpenCV from v1 to v4
- Tesseract OCR
- installing, on operating system / Installing Tesseract OCR on your operating system
- installing, on Windows / Installing Tesseract on Windows
- library, building / Building the latest library
- setting up, in Visual Studio / Setting up Tesseract in Visual Studio
- installing, on Mac / Installing Tesseract on Mac
- Tesseract OCR library
- using / Using the Tesseract OCR library
- function, creating / Creating an OCR function
- file output, sending / Sending the output to a file
- text API
- working / How the text API works
- scene detection problem / The scene detection problem
- extremal region / Extremal regions
- extremal region, filtering / Extremal region filtering
- using / Using the text API
- text detection / Text detection
- text extraction / Text extraction
- text recognition / Text recognition
- text detection
- about / Text detection and recognition, Text detection
- parameters / Text detection
- text extraction
- about / Text extraction
- parameters / Text extraction
- text recognition
- about / Text detection and recognition, Text recognition
- parameters / Text recognition
- text segmentation
- about / Text segmentation
- connected areas, creating / Creating connected areas
- paragraph blocks, identifying / Identifying paragraph blocks
- text extraction / Text extraction and skewing adjustment
- skewing adjustment / Text extraction and skewing adjustment
- Top Hat transform
- about / Top Hat transform
- performing / Top Hat transform
- train function
- TrainData / OpenCV machine learning algorithms
- samples / OpenCV machine learning algorithms
- layout / OpenCV machine learning algorithms
- responses / OpenCV machine learning algorithms
- flags / OpenCV machine learning algorithms
- Transparent API (T-API) / History of OpenCV from v1 to v4
- transposition / Basic matrix operations
- triangulation / Stereo reconstruction and SfM
U
- upper bits / Segmentation
- UV4L / Streaming video from Raspberry Pi to a powerful computer
V
- Vec object type / Vec object type
- video
- streaming, from Raspberry Pi to powerful computer / Streaming video from Raspberry Pi to a powerful computer
- video-surveillance systems
- technical requisites / Technical requirements, Technical requirements
- video analysis / Video analysis
- videos
- reading / Reading videos and cameras
- Visual C++ Package Manager
- Visual Studio / Basic CMake configuration file
W
- warpAffine function
- SRC arguments / Text extraction and skewing adjustment
- DST arguments / Text extraction and skewing adjustment
- M arguments / Text extraction and skewing adjustment
- SIZE / Text extraction and skewing adjustment
- webcam
- accessing / Accessing the webcam
Y
- Y'CrCb color space / Implementation of the skin color changer
- Yet Another Computer Vision Index To Datasets (YACVID)
- YOLO algorithm
- about / YOLO – real-time object detection
- v3 deep learning model architecture / YOLO v3 deep learning model architecture
- dataset / The YOLO dataset, vocabulary, and model
- model / The YOLO dataset, vocabulary, and model
- vocabulary / The YOLO dataset, vocabulary, and model
- importing, into OpenCV / Importing YOLO into OpenCV
- you only look once (YOLO)