All Classes and Interfaces
Class
Description
Class for implementing the wrapper which makes detectors and extractors to be affine invariant,
described as ASIFT in CITE: YM11 .
This is a base class for all more or less complex algorithms in OpenCV
especially for classes of algorithms, for which there can be multiple implementations.
The base class for algorithms that align images of the same scene with different exposures
This algorithm converts images to median threshold bitmaps (1 for pixels brighter than median
luminance and 0 otherwise) and than aligns the resulting bitmaps using bit operations.
Represents an animation with multiple frames.
Artificial Neural Networks - Multi-Layer Perceptrons.
*************************************************************************************\
Approximate Nearest Neighbors *
\***************************************************************************************
The main functionality of ArucoDetector class is detection of markers in an image with detectMarkers() method.
Computes average hash value of the input image
This is a fast image hashing algorithm, but only work on simple case.
Base class for background/foreground segmentation.
K-nearest neighbours - based Background/Foreground Segmentation Algorithm.
Gaussian Mixture-based Background/Foreground Segmentation Algorithm.
Brute-force descriptor matcher.
Image hash based on block mean.
Board of ArUco markers
A board is a set of markers in the 3D space with a common coordinate system.
Boosted tree classifier derived from DTrees
SEE: REF: ml_intro_boost
The base class for camera response calibration algorithms.
Inverse camera response function is extracted for each brightness value by minimizing an objective
function as linear system.
Inverse camera response function is extracted for each brightness value by minimizing an objective
function as linear system.
Cascade classifier class for object detection.
CChecker
checker object
This class contains the information about the detected checkers,i.e, their
type, the corners of the chart, the color profile, the cost, centers chart,
etc.
A class to find the positions of the ColorCharts in the image.
ChArUco board is a planar chessboard where the markers are placed inside the white squares of a chessboard.
Base class for Contrast Limited Adaptive Histogram Equalization.
This class represents high-level API for classification models.
Core class of ccm model
Produce a ColorCorrectionModel instance for inference
Image hash based on color moments.
Base class for dense optical flow algorithms
Abstract base class for matching keypoint descriptors.
This class represents high-level API for object detection networks.
struct DetectorParameters is used by ArucoDetector
struct DetectorParametersMCC is used by CCheckerDetector
Dictionary is a set of unique ArUco markers of the same size
bytesList storing as 2-dimensions Mat with 4-th channels (CV_8UC4 type was used) and contains the marker codewords where:
- bytesList.rows is the dictionary size
- each marker is encoded using nbytes = ceil(markerSize*markerSize/8.) bytes
- each row contains all 4 rotations of the marker, so its length is 4*nbytes
- the byte order in the bytesList[i] row:
//bytes without rotation/bytes with rotation 1/bytes with rotation 2/bytes with rotation 3//
So bytesList.ptr(i)[k*nbytes + j] is the j-th byte of i-th marker, in its k-th rotation.This struct stores the scalar value (or array) of one of the following type: double, cv::String or int64.
DIS optical flow algorithm.
Structure for matching: query descriptor index, train descriptor index, train
image index and distance between descriptors.
A class to upscale images via convolutional neural networks.
The class represents a single decision tree or a collection of decision trees.
struct ECCParameters is used by findTransformECCMultiScale
motionType parameter, specifying the type of motion:
MOTION_TRANSLATION sets a translational motion model; warpMatrix is \(2\times 3\) with
the first \(2\times 2\) part being the unity matrix and the rest two parameters being
estimated.
The class implements the Expectation Maximization algorithm.
Base class for 1st and 2nd stages of Neumann and Matas scene text detection algorithm CITE: Neumann12.
Callback with the classifier is made a class.
DNN-based face detector
model download link: https://github.com/opencv/opencv_zoo/tree/master/models/face_detection_yunet
DNN-based face recognizer
model download link: https://github.com/opencv/opencv_zoo/tree/master/models/face_recognition_sface
Class computing a dense optical flow using the Gunnar Farneback's algorithm.
Wrapping class for feature detection using the FAST method.
Abstract base class for 2D image feature detectors and descriptor extractors
Flann-based descriptor matcher.
Wrapper on top of a truetype/opentype/etc font, i.e.
finds arbitrary template in the grayscale image using Generalized Hough Transform
finds arbitrary template in the grayscale image using Generalized Hough Transform
Detects position only without translation and rotation CITE: Ballard1981 .
finds arbitrary template in the grayscale image using Generalized Hough Transform
Detects position, translation and rotation CITE: Guil1999 .
Wrapping class for feature detection using the goodFeaturesToTrack function.
Gray-world white balance algorithm
This algorithm scales the values of pixels based on a
gray-world assumption which states that the average of all channels
should result in a gray image.
Planar board with grid arrangement of markers
More common type of board.
This class was designed for use in Java applications
to recreate the OpenCV HighGui functionalities.
Class implementing two-dimensional phase unwrapping based on CITE: histogramUnwrapping
This algorithm belongs to the quality-guided phase unwrapping methods.
Parameters of phaseUnwrapping constructor.
Implementation of HOG (Histogram of Oriented Gradients) descriptor and object detector.
Processing params of image to blob.
This class was designed to create and manipulate
the Windows to be used by the HighGui class.
The base class for image hash algorithms
Intelligent Scissors image segmentation
This class is used to find the path (contour) between two points
which can be used for image segmentation.
Read data stream interface
Kalman filter class.
This class represents high-level API for keypoints models
KeypointsModel allows to set params for preprocessing input image.
The class implements K-Nearest Neighbors model
SEE: REF: ml_intro_knn
This interface class allows to build new Layers - are building blocks of networks.
More sophisticated learning-based automatic white balance algorithm.
This class is used to track multiple objects using the specified tracker algorithm.
Base abstract class for the long-term tracker:
the Boosting tracker
This is a real-time object tracking based on a novel on-line version of the AdaBoost algorithm.
the CSRT tracker
The implementation is based on CITE: Lukezic_IJCV2018 Discriminative Correlation Filter with Channel and Spatial Reliability
the KCF (Kernelized Correlation Filter) tracker
KCF is a novel tracking framework that utilizes properties of circulant matrix to enhance the processing speed.
the Median Flow tracker
Implementation of a paper CITE: MedianFlow .
The MIL algorithm trains a classifier in an online manner to separate the object from the
background.
the MOSSE (Minimum Output Sum of Squared %Error) tracker
The implementation is based on CITE: MOSSE Visual Object Tracking using Adaptive Correlation Filters
Note: this tracker works with grayscale images, if passed bgr ones, they will get converted internally.
the TLD (Tracking, learning and detection) tracker
TLD is a novel tracking framework that explicitly decomposes the long-term tracking task into
tracking, learning and detection.
Line segment detector class
following the algorithm described at CITE: Rafael12 .
Implements Logistic Regression classifier.
Marr-Hildreth Operator Based Hash, slowest but more discriminative.
The resulting HDR image is calculated as weighted average of the exposures considering exposure
values and camera response.
The base class algorithms that can merge exposure sequence to a single image.
Pixels are weighted using contrast, saturation and well-exposedness measures, than images are
combined using laplacian pyramids.
The resulting HDR image is calculated as weighted average of the exposures considering exposure
values and camera response.
This class is presented high-level API for neural networks.
******************************* Motion Saliency Base Class *********************************
the Fast Self-tuning Background Subtraction Algorithm from CITE: BinWangApr2014
Maximally stable extremal region extractor
The class encapsulates all the parameters of the %MSER extraction algorithm (see [wiki
article](http://en.wikipedia.org/wiki/Maximally_stable_extremal_regions)).
Represents an edge in a graph for Minimum Spanning Tree (MST) computation.
This class allows to create and manipulate comprehensive artificial neural networks.
Bayes classifier for normally distributed data.
******************************* Objectness Base Class *********************************
the Binarized normed gradients algorithm from CITE: BING
OCRBeamSearchDecoder class provides an interface for OCR using Beam Search algorithm.
Callback with the character classifier is made a class.
OCRHMMDecoder class provides an interface for OCR using Hidden Markov Models.
Callback with the character classifier is made a class.
OCRTesseract class provides an interface with the tesseract-ocr API (v3.02.02) in C++.
Octree for 3D vision.
An object that keeps per-frame data for Odometry algorithms from user-provided images to algorithm-specific precalculated data.
Dummy interface to allow some integration testing within OSGi implementation.
This class is intended to provide a convenient way to load OpenCV's native
library from the Java bundle.
Class implementing the ORB (*oriented BRIEF*) keypoint detector and descriptor extractor
described in CITE: RRKB11 .
The structure represents the logarithmic grid range of statmodel parameters.
Abstract base class for phase unwrapping.
pHash
Slower than average_hash, but tolerant of minor modifications
This algorithm can combat more variation than averageHash, for more details please refer to CITE: lookslikeit
plot Plot function for Mat data
Base class for Levenberg-Marquadt solvers.
QR code detector.
QR code detector based on Aruco markers detection code.
QR code encoder.
QR code encoder parameters.
Image hash based on Radon transform.
struct RefineParameters is used by ArucoDetector
class which allows the Gipsa/Listic Labs model to be used with OpenCV.
a wrapper class which allows the tone mapping algorithm of Meylan&al(2007) to be used with OpenCV.
Object that can compute the normals in an image.
The class implements the random forest predictor.
******************************* Saliency Base Class *********************************
This class represents high-level API for segmentation models
SegmentationModel allows to set params for preprocessing input image.
Class for extracting keypoints and computing descriptors using the Scale Invariant Feature Transform
(SIFT) algorithm by D.
Class for extracting blobs from an image.
A simple white balance algorithm that works by independently stretching
each of the input image channels to the specified range.
Base interface for sparse optical flow algorithms.
Class used for calculating a sparse optical flow.
******************************* Static Saliency Base Class *********************************
the Fine Grained Saliency approach from CITE: FGS
This method calculates saliency based on center-surround differences.
the Spectral Residual approach from CITE: SR
Starting from the principle of natural image statistics, this method simulate the behavior of
pre-attentive visual search.
Base class for statistical models in OpenCV ML.
Class for computing stereo correspondence using the block matching algorithm, introduced and
contributed to OpenCV by K.
The base class for stereo correspondence algorithms.
The class implements the modified H.
Support Vector Machines.
*************************************************************************************\
Stochastic Gradient Descent SVM Classifier *
\***************************************************************************************
Base class for text detection networks
This class represents high-level API for text detection DL networks compatible with DB model.
This class represents high-level API for text detection DL networks compatible with EAST model.
An abstract class providing interface for text detection algorithms
TextDetectorCNN class provides the functionallity of text bounding box detection.
This class represents high-level API for text recognition networks.
a Class to measure passing time.
High-level tokenizer wrapper for DNN usage.
Base class for tonemapping algorithms - tools that are used to map HDR image to 8-bit range.
Adaptive logarithmic mapping is a fast global tonemapping algorithm that scales the image in
logarithmic domain.
This algorithm decomposes image into two layers: base layer and detail layer using bilateral filter
and compresses contrast of the base layer thus preserving all the details.
This algorithm transforms image to contrast using gradients on all levels of gaussian pyramid,
transforms contrast values to HVS response and scales the response.
This is a global tonemapping operator that models human visual system.
Base abstract class for the long-term tracker
the CSRT tracker
The implementation is based on CITE: Lukezic_IJCV2018 Discriminative Correlation Filter with Channel and Spatial Reliability
the KCF (Kernelized Correlation Filter) tracker
KCF is a novel tracking framework that utilizes properties of circulant matrix to enhance the processing speed.
The MIL algorithm trains a classifier in an online manner to separate the object from the
background.
the Nano tracker is a super lightweight dnn-based general object tracking.
the VIT tracker is a super lightweight dnn-based general object tracking.
Class encapsulating training data.
class which provides a transient/moving areas segmentation module
perform a locally adapted segmentation by using the retina magno input data Based on Alexandre
BENOIT thesis: "Le système visuel humain au secours de la vision par ordinateur"
3 spatio temporal filters are used:
a first one which filters the noise and local variations of the input motion energy
a second (more powerfull low pass spatial filter) which gives the neighborhood motion energy the
segmentation consists in the comparison of these both outputs, if the local motion energy is higher
to the neighborhood otion energy, then the area is considered as moving and is segmented
a stronger third low pass filter helps decision by providing a smooth information about the
"motion context" in a wider area
Structure to keep settings for rasterization
Variational optical flow refinement
This class implements variational refinement of the input flow field, i.e.
Class for video capturing from video files, image sequences or cameras.
Video writer class.
WeChat QRCode includes two CNN-based models:
A object detection model and a super resolution model.
The base class for auto white balance algorithms.