Index
A
- active illumination or structured light
- active imaging systems
- about / Coloring the light
- Active Shape Model
- actual model training
- Android-specific tasks
- defining / Android specifics
- threaded overlay / Threaded overlay
- media files, reading / Reading media files
- Android NDK
- Android Studio
- OpenCV, integrating into / Integrating OpenCV into the Android Studio
- setting up, with OpenCV / Setting up the Android Studio to work with OpenCV
- Android Studio project
- OpenCV Android SDK, compiling to / Compiling OpenCV Android SDK to the Android Studio project
- aperture priority (A)
- aperture setting
- application showcase
- about / Application showcase
- application specific training data
- selecting / Smartly selecting and preparing application specific training data
- preparing / Smartly selecting and preparing application specific training data
- amount of training data / The amount of training data
- object annotation files, creating for positive samples / Creating object annotation files for the positive samples
- positive dataset, parsing into OpenCV data vector / Parsing your positive dataset into the OpenCV data vector
- application user interface, Android section
- defining / The Android section – an application user interface
- setup activity layout / The setup activity layout
- camera frame, capturing / Capturing the camera frame
- Capture button, implementing / Implementing the Capture button
- Save button, implementing / Implementing the Save button
- ASCII codes
- ASUS Xtion PRO Live
- automatic facial expression recognition
- problems / Introducing facial expression recognition
B
- B&H
- URL / Shopping for glass
- biometrics
- about / Biometrics, a general approach
- training dataset, obtaining / Step 1 – getting a good training dataset and applying application-specific normalization
- application-specific normalization, applying / Step 1 – getting a good training dataset and applying application-specific normalization
- descriptor of recorded biometric, creating / Step 2 – creating a descriptor of the recorded biometric
- machine learning, for matching retrieved feature vector / Step 3 – using machine learning to match the retrieved feature vector
- authentication process / Step 4 – think about your authentication process
- bootstrapping process / Increasing object instance detection and reducing false positive detections
C
- calibration
- about / Calibration
- unknown parameters / Calibration
- data structures / Data structures
- rotations, handling / Handling rotations
- class / The calibration class
- images, undistorting / Undistorting images
- results, testing / Testing calibration results
- camera frame
- capturing / Capturing the camera frame
- obtaining, Camera API used / Using the Camera API to get the camera frame
- Camera Selector tool
- Camera Sensor Review publications
- camera trap
- planning / Planning the camera trap
- cascade classification process
- about / The cascade classification process in detail
- negative samples, grabbing / Step 1 – grabbing positive and negative samples
- positive samples, grabbing / Step 1 – grabbing positive and negative samples
- integral image, precalculation / Step 2 – precalculation of integral image and all possible features from the training data
- features, precalculation / Step 2 – precalculation of integral image and all possible features from the training data
- boosting process, firing up / Step 3 – firing up the boosting process
- temporary result, saving to stage file / Step 4 – saving the temporary result to a stage file, The resulting object model explained in detail
- HAAR-like wavelet feature models / HAAR-like wavelet feature models
- local binary pattern models / Local binary pattern models
- visualization tool, for object models / Visualization tool for object models
- cascade classification training tool
- CASIA eye dataset
- reference / Iris identification, how is it done?
- catalogue
- URL / Shopping for glass
- chromatic aberrations
- about / Shopping for glass
- classification
- defining / Classification
- process / Classification process
- CodecOutputSurface
- URL / Reading media files
- Code Laboratories (CL)
- colorful images
- references / Detecting a colorful subject
- convolutions
- about / The calibration class
D
- 2D Features Framework documentation
- 2D scale space relation
- about / 2D scale space relation
- data
- capturing / Capturing data
- video, recording / Recording video
- gyro signals, recording / Recording gyro signals
- data collection
- data normalization, on detected face regions
- about / Data normalization on the detected face regions
- face recognition approaches / Various face recognition approaches and their corresponding feature space
- Eigenface decomposition, through PCA / Eigenface decomposition through PCA
- linear discriminant analysis, Fisher criterion used / Linear discriminant analysis using the Fisher criterion
- local binary pattern histograms / Local binary pattern histograms
- dataset
- dataset bias / Step 1 – getting a good training dataset and applying application-specific normalization
- data structures
- about / Data structures
- gyroscope trace, reading / Reading the gyroscope trace
- training video / The training video
- depth map
- depth of field
- descriptors
- URL / Advanced features
- detection result
- optimizing, with scene specific knowledge and constraints / Using scene specific knowledge and constraints to optimize the detection result
- influencing, with parameters of detection command / Using the parameters of the detection command to influence your detection result
- object instance detection, increasing / Increasing object instance detection and reducing false positive detections
- false positive detections, reducing / Increasing object instance detection and reducing false positive detections
- digital single-lens reflex (DSLR) camera
- about / Planning the camera trap
- dimensionality reduction
- defining / Dimensionality reduction
- distribution, of feature representation
- computing, over k clusters / Computing the distribution of feature representation over k clusters
- do-it-yourself (DIY) kits
- dynamic scene
- and static scene, comparing / Detecting the presence of a photogenic subject
E
- efficiency
- electromagnetic radiation types
- radio waves / Coloring the light
- microwaves / Coloring the light
- far infrared (FIR) light / Coloring the light
- near infrared (NIR) light / Coloring the light
- visible light / Coloring the light
- ultraviolet (UV) light / Coloring the light
- x-rays / Coloring the light
- gamma rays / Coloring the light
- evaluation
- defining / Evaluation
- with different learning algorithms / Evaluation with different learning algorithms
- with different features / Evaluation with different features
- different number of clusters / Evaluation with a different number of clusters
- exposure bracketing
- about / Planning the camera trap
- shell script, writing for / Writing a shell script for exposure bracketing
- exposure compensation
- exposure value (EV)
- extension tube
- about / Shopping for glass
F
- f-number
- f-stop
- Face Alignment
- face detection
- about / Face detection and recognition
- Viola and Jones boosted cascade classifier algorithm used / Face detection using the Viola and Jones boosted cascade classifier algorithm
- reference / Face detection using the Viola and Jones boosted cascade classifier algorithm
- data normalization, on detected face regions / Data normalization on the detected face regions
- data normalization, on detected face region / Data normalization on the detected face regions
- face detection algorithm
- used, for extracting face region / Extracting the face region using a face detection algorithm
- face region
- finding, in image / Finding the face region in the image
- extracting, face detection algorithm used / Extracting the face region using a face detection algorithm
- facial landmarks, extracting from / Extracting facial landmarks from the face region
- extracting / Extracting the face region
- facial expression dataset
- about / Facial expression dataset
- facial expression recognition
- defining / Introducing facial expression recognition
- facial landmarks
- extracting, from face region / Extracting facial landmarks from the face region
- about / Facial landmarks
- defining / What are facial landmarks?
- URL / What are facial landmarks?
- detecting / How do you detect facial landmarks?
- using / How do you use facial landmarks?
- facial recognition
- feature extraction
- defining / Feature extraction
- feature extractions
- improving / Improving feature extraction
- Field of view (FOV)
- final feature
- computing, for each image / Computing a final feature for each image
- fingerprint identification
- about / Fingerprint identification, how is it done?
- performing / Fingerprint identification, how is it done?
- approach, implementing in OpenCV 3 / Implementing the approach in OpenCV 3
- fingerprint software
- reference / Implementing the approach in OpenCV 3
- flandmark library
- defining / Introducing the flandmark library
- URL / Introducing the flandmark library, Downloading and compiling the flandmark library
- downloading / Downloading and compiling the flandmark library
- compiling / Downloading and compiling the flandmark library
- facial landmarks, detecting with / Detecting facial landmarks with flandmark
- Flickr
- URL / Shopping for glass
- FlyCapture2 SDK (FC2)
- focal length
- focus distance
- foreground mask
- about / Detecting a moving subject
G
- general face detector / Face detection and recognition
- glass
- defining / Shopping for glass
- global shutter
- Gnome Virtual File System (GVFS)
- gPhoto2
- about / Controlling a photo camera with gPhoto2
- photo camera, controlling with / Controlling a photo camera with gPhoto2
- URL / Controlling a photo camera with gPhoto2
- testing / Setting up and testing gPhoto2
- setting up / Setting up and testing gPhoto2
- wrapping / Writing a Python script to wrap gPhoto2
- gPhoto2-compatible camera
- GPU optimizations
- about / Performance evaluation and GPU optimizations
- performing / Optimizations using GPU code
- GS3-U3-23S6M-C model
- supercharging / Supercharging the GS3-U3-23S6M-C and other Point Grey Research cameras
- using / Shopping for glass
- gyroscope axes
- identifying / Identifying gyroscope axes
H
- -h parameter / Parsing your positive dataset into the OpenCV data vector
- HAAR-like wavelet feature models
- about / HAAR-like wavelet feature models
- node left and node right / HAAR-like wavelet feature models
- node feature index / HAAR-like wavelet feature models
- node threshold / HAAR-like wavelet feature models
- hard negative mining / Increasing object instance detection and reducing false positive detections
- HDR images
- creating / Creating HDR images
- HDR imaging and tone mapping
- references / Creating HDR images
- helper function
- about / Accumulated rotations
- high dynamic range (HDR)
- about / Planning the camera trap
- high quality object samples / The amount of training data
- histogram equalization / Face detection using the Viola and Jones boosted cascade classifier algorithm
- hybrid solution
- defining, of hardware and software / A hybrid of hardware and software
- hyper parameter optimization techniques / Step 3 – using machine learning to match the retrieved feature vector
I
- -info parameter / Parsing your positive dataset into the OpenCV data vector
- image
- landmarks, visualizing / Visualizing the landmarks in an image
- image features
- extracting, from facial component regions / Extracting image features from facial component regions
- contributed features / Extracting image features from facial component regions, Contributed features
- advanced features / Extracting image features from facial component regions, Advanced features
- key points, visualizing / Visualizing key points for each feature type
- image features space
- clustering, into k clusters / Clustering image features space into k clusters
- image formats
- raw image / Coloring the light
- packed image / Coloring the light
- planar image / Coloring the light
- image matching comparison
- URL / Advanced features
- images
- processing / Processing images to show subtle colors and motion
- reference / Processing images to show subtle colors and motion
- HDR images, creating / Creating HDR images
- time-lapse videos, creating / Creating time-lapse videos
- iris identification
- about / Iris identification, how is it done?
- performing / Iris identification, how is it done?
- approach, implementing in OpenCV 3 / Implementing the approach in OpenCV 3
- ISO speed
J
- Japanese Female Facial Expression (JAFFE)
- about / Facial expression dataset
- URL / Facial expression dataset
- Java and C++ interaction
- creating, with JNI / Creating a Java and C++ interaction with Java Native Interface (JNI)
- Java Native Interface (JNI)
- JNI documentation
- JNI tips, from API guides
K
- K-fold cross validation
- defining / K-fold cross validation
- K-Nearest Neighbors (KNN)
- about / K-Nearest Neighbors (KNN)
- training stage / Training stage
- testing stage / The testing stage
- Kaggle
- Kaggle facial expression dataset
- about / Kaggle facial expression dataset
- k clusters
- image features space, clustering into / Clustering image features space into k clusters
L
- LBP feature-based model
- about / Local binary pattern models
- node left and node right / Local binary pattern models
- node feature index / Local binary pattern models
- eight 32-bit values / Local binary pattern models
- learning rate
- about / Detecting a moving subject
- lenses
- examples / Shopping for glass
- libgphoto2
- finding / Finding libgphoto2 and wrappers
- URL / Finding libgphoto2 and wrappers
- light
- coloring / Coloring the light
- line pairs per millimeter
- live view
- about / Planning the camera trap
M
- macam
- machine learning techniques
- similarity matching / Step 3 – using machine learning to match the retrieved feature vector
- K-Nearest neighbours search / Step 3 – using machine learning to match the retrieved feature vector
- Naïve Bayes classifiers / Step 3 – using machine learning to match the retrieved feature vector
- support vector machines / Step 3 – using machine learning to match the retrieved feature vector
- boosting and random forests / Step 3 – using machine learning to match the retrieved feature vector
- artificial neural networks / Step 3 – using machine learning to match the retrieved feature vector
- MacPorts
- macropixels
- about / Coloring the light
- manual exposure (M)
- math
- about / The math
- camera model / The camera model
- camera motion / The Camera motion
- shutter compensation, rolling / Rolling shutter compensation
- image warping / Image warping
- Mathias Appel
- memcpy
- MFlenses
- URL / Shopping for glass
- mirror lock-up (MLU)
- about / Planning the camera trap
- monochrome (gray) images
- about / Coloring the light
- motion analysis and object tracking
- Motion Sensors API documentation
- URL / Further improvement
- multi-layer perceptron
- defining / Multi-layer perceptron
- training stage / Training stage
- network, defining / Define the network
- network, training / Train the network
- testing stage / Testing stage
- multiprocessing module
N
- -num parameter / Parsing your positive dataset into the OpenCV data vector
- natural occurring samples / The amount of training data
- NDK/JNI
- OpenCV C++, compiling with / Compiling OpenCV C++ with NDK/JNI
- negative sample generation
- reference / The amount of training data
- Normal Bayes classifier
- about / Normal Bayes classifier
- training stage / Training stage
- testing stage / Testing stage
- normal lens
- about / Shopping for glass
O
- object annotation
- object categorization
- object detection
- object recognition
- omitted sections, script
- OpenCV
- integrating, into Android Studio / Integrating OpenCV into the Android Studio
- OpenCV, for Android
- OpenCV 3
- URL / Software usage guide
- OpenCV Android SDK
- compiling, to Android Studio project / Compiling OpenCV Android SDK to the Android Studio project
- importing / Importing the OpenCV Android SDK
- OpenCV C++
- compiling, with NDK/JNI / Compiling OpenCV C++ with NDK/JNI
- OpenCV C++ code
- implementing / Implementing the OpenCV C++ code
- OpenCV Java code
- implementing / Implementing the OpenCV Java code
- opencv_contrib module
- compiling / Compiling the opencv_contrib module
- OpenNI
- OpenNI-compliant depth cameras
- OpenNI2
- OpenSUSE, gPhoto2
P
- Panorama
- defining / Introducing the concept of panorama
- Android section / Introducing the concept of panorama
- OpenCV section / Introducing the concept of panorama
- panorama application
- about / Further improvement
- parameters, accumulated rotations
- about / Accumulated rotations
- parameter selection, for training object model
- about / Parameter selection when training an object model
- parameters, training / Training parameters involved in training an object model
- cascade classification process / The cascade classification process in detail
- resulting object model / The resulting object model explained in detail
- cross-validation, using / Using cross-validation to achieve the best model possible
- parameters training, in object model
- about / Training parameters involved in training an object model
- -data / Training parameters involved in training an object model
- -numPos / Training parameters involved in training an object model
- -numNeg / Training parameters involved in training an object model
- -numStages / Training parameters involved in training an object model
- -bg / Training parameters involved in training an object model
- -vec / Training parameters involved in training an object model
- -precalcValBufSize / Training parameters involved in training an object model
- -precalcIdxBufSize / Training parameters involved in training an object model
- -featureType / Training parameters involved in training an object model
- -minHitRate / Training parameters involved in training an object model
- -maxFalseAlarmRate / Training parameters involved in training an object model
- passive imaging systems
- about / Coloring the light
- people registration system
- creating, by combining techniques / Combining the techniques to create an efficient people-registration system
- performance evaluation
- about / Performance evaluation and GPU optimizations
- object detection performance testing / Object detection performance testing
- PGR
- PGR camera
- photo camera
- controlling, with gPhoto2 / Controlling a photo camera with gPhoto2
- photogenic subject presence
- detecting / Detecting the presence of a photogenic subject
- moving subject, detecting / Detecting a moving subject
- colorful subject, detecting / Detecting a colorful subject
- face of mammal, detecting / Detecting the face of a mammal
- photosites
- about / Coloring the light
- Picture Transfer Protocol (PTP)
- PlayStation Eye
- supercharging / Supercharging the PlayStation Eye
- Point Grey Research cameras
- practical applications
- about / Practical applications
- precision
- Principle Component Analysis (PCA)
- about / Dimensionality reduction
- project
- defining / Project overview
- PS3EYEDriver
- python-gphoto2
- Python pickle module
- using / Use the Python pickle module
- Python script
- writing, to wrap gPhoto2 / Writing a Python script to wrap gPhoto2
R
- RANSAC
- about / The training video
- recall
- recognition
- region of interest (ROI)
- repository, of calibration parameters
- resolution
- rolling shutter
- rolling shutter direction
- estimating / Estimating the rolling shutter direction
- rolling shutter with global reset
- rotation invariance object detection
- obtaining / Obtaining rotation invariance object detection
- rotations
- image, rotating / Rotating an image
- accumulated rotations / Accumulated rotations
S
- sample counting tool
- sample creation tool
- SensorKinect
- sensor sizes, in machine vision cameras
- URL / Shopping for glass
- shell script
- writing, to unmount camera drives / Writing a shell script to unmount camera drives
- writing, for exposure bracketing / Writing a shell script for exposure bracketing
- shutter compensation
- rolling / Rolling shutter compensation
- rolling shutter, calibrating / Calibrating the rolling shutter
- warping, with grid points / Warping with grid points
- unwarping, with calibration / Unwarping with calibration
- shutter speed
- Simple DirectMedia Layer 2 (SDL2)
- single images
- writing / Write out single images
- smoother timelapses
- about / Smoother timelapses
- software usage guide
- defining / Software usage guide, Software usage guide, Software usage guide
- source code, driver
- source code, LookSpry
- source code, Unblinking Eye
- source code and build files, Infravision
- spectral response
- about / Coloring the light
- spherical aberrations
- about / Shopping for glass
- stabilization
- with images / Stabilization with images
- with images, reference / Stabilization with images
- with hardware / Stabilization with hardware
- with hardware, reference / Stabilization with hardware
- Stitcher class
- URL / Further improvement
- Stitching module
- URL / Further improvement
- stump weak classifiers / Training parameters involved in training an object model
- subject
- capturing, in moment / Capturing the subject in the moment
- subprocess module
- supported methods, of histogram comparison
- Support Vector Machine (SVM)
- defining / Support vector machines
- training stage / Training stage
- testing stage / Testing stage
- system overview
- about / System overview
T
- T-number
- T-stop
- Technical Application Note (TAN)
- Technical Reference Manual
- testing
- without delta / Testing without the delta
- throughput
- about / Capturing the subject in the moment
- factors / Capturing the subject in the moment
- time-lapse videos
- creating / Creating time-lapse videos
- tone mapping
- about / Creating HDR images
- translations
- incorporating / Incorporating translations
- transmittance
U
- unusual suspects
- rounding up / Rounding up the unusual suspects
V
- -vec parameter / Parsing your positive dataset into the OpenCV data vector
- validation
- vignetting
- about / Shopping for glass
W
- -w parameter / Parsing your positive dataset into the OpenCV data vector
- white paper, PGR
- wrappers
- finding / Finding libgphoto2 and wrappers
X
- Xtion devices
- Xtion PRO Live
Y
- YUV channels
- about / Coloring the light