1 Feature Detection and Description
2 =================================
8 * An example explaining keypoint detection and description can be found at opencv_source_code/samples/cpp/descriptor_extractor_matcher.cpp
12 Detects corners using the FAST algorithm
14 .. ocv:function:: void FAST( InputArray image, vector<KeyPoint>& keypoints, int threshold, bool nonmaxSuppression=true )
15 .. ocv:function:: void FAST( InputArray image, vector<KeyPoint>& keypoints, int threshold, bool nonmaxSuppression, int type )
17 :param image: grayscale image where keypoints (corners) are detected.
19 :param keypoints: keypoints detected on the image.
21 :param threshold: threshold on difference between intensity of the central pixel and pixels of a circle around this pixel.
23 :param nonmaxSuppression: if true, non-maximum suppression is applied to detected corners (keypoints).
25 :param type: one of the three neighborhoods as defined in the paper: ``FastFeatureDetector::TYPE_9_16``, ``FastFeatureDetector::TYPE_7_12``, ``FastFeatureDetector::TYPE_5_8``
27 Detects corners using the FAST algorithm by [Rosten06]_.
29 .. note:: In Python API, types are given as ``cv2.FAST_FEATURE_DETECTOR_TYPE_5_8``, ``cv2.FAST_FEATURE_DETECTOR_TYPE_7_12`` and ``cv2.FAST_FEATURE_DETECTOR_TYPE_9_16``. For corner detection, use ``cv2.FAST.detect()`` method.
32 .. [Rosten06] E. Rosten. Machine Learning for High-speed Corner Detection, 2006.
36 .. ocv:class:: MSER : public FeatureDetector
38 Maximally stable extremal region extractor. ::
40 class MSER : public CvMSERParams
43 // default constructor
45 // constructor that initializes all the algorithm parameters
46 MSER( int _delta, int _min_area, int _max_area,
47 float _max_variation, float _min_diversity,
48 int _max_evolution, double _area_threshold,
49 double _min_margin, int _edge_blur_size );
50 // runs the extractor on the specified image; returns the MSERs,
51 // each encoded as a contour (vector<Point>, see findContours)
52 // the optional mask marks the area where MSERs are searched for
53 void detectRegions( InputArray image, vector<vector<Point> >& msers, vector<Rect>& bboxes ) const;
56 The class encapsulates all the parameters of the MSER extraction algorithm (see
57 http://en.wikipedia.org/wiki/Maximally_stable_extremal_regions). Also see http://code.opencv.org/projects/opencv/wiki/MSER for useful comments and parameters description.
61 * (Python) A complete example showing the use of the MSER detector can be found at opencv_source_code/samples/python2/mser.py
66 .. ocv:class:: ORB : public Feature2D
68 Class implementing the ORB (*oriented BRIEF*) keypoint detector and descriptor extractor, described in [RRKB11]_. The algorithm uses FAST in pyramids to detect stable keypoints, selects the strongest features using FAST or Harris response, finds their orientation using first-order moments and computes the descriptors using BRIEF (where the coordinates of random point pairs (or k-tuples) are rotated according to the measured orientation).
70 .. [RRKB11] Ethan Rublee, Vincent Rabaud, Kurt Konolige, Gary R. Bradski: ORB: An efficient alternative to SIFT or SURF. ICCV 2011: 2564-2571.
76 .. ocv:function:: ORB::ORB(int nfeatures = 500, float scaleFactor = 1.2f, int nlevels = 8, int edgeThreshold = 31, int firstLevel = 0, int WTA_K=2, int scoreType=ORB::HARRIS_SCORE, int patchSize=31)
78 .. ocv:pyfunction:: cv2.ORB([, nfeatures[, scaleFactor[, nlevels[, edgeThreshold[, firstLevel[, WTA_K[, scoreType[, patchSize]]]]]]]]) -> <ORB object>
81 :param nfeatures: The maximum number of features to retain.
83 :param scaleFactor: Pyramid decimation ratio, greater than 1. ``scaleFactor==2`` means the classical pyramid, where each next level has 4x less pixels than the previous, but such a big scale factor will degrade feature matching scores dramatically. On the other hand, too close to 1 scale factor will mean that to cover certain scale range you will need more pyramid levels and so the speed will suffer.
85 :param nlevels: The number of pyramid levels. The smallest level will have linear size equal to ``input_image_linear_size/pow(scaleFactor, nlevels)``.
87 :param edgeThreshold: This is size of the border where the features are not detected. It should roughly match the ``patchSize`` parameter.
89 :param firstLevel: It should be 0 in the current implementation.
91 :param WTA_K: The number of points that produce each element of the oriented BRIEF descriptor. The default value 2 means the BRIEF where we take a random point pair and compare their brightnesses, so we get 0/1 response. Other possible values are 3 and 4. For example, 3 means that we take 3 random points (of course, those point coordinates are random, but they are generated from the pre-defined seed, so each element of BRIEF descriptor is computed deterministically from the pixel rectangle), find point of maximum brightness and output index of the winner (0, 1 or 2). Such output will occupy 2 bits, and therefore it will need a special variant of Hamming distance, denoted as ``NORM_HAMMING2`` (2 bits per bin). When ``WTA_K=4``, we take 4 random points to compute each bin (that will also occupy 2 bits with possible values 0, 1, 2 or 3).
93 :param scoreType: The default HARRIS_SCORE means that Harris algorithm is used to rank features (the score is written to ``KeyPoint::score`` and is used to retain best ``nfeatures`` features); FAST_SCORE is alternative value of the parameter that produces slightly less stable keypoints, but it is a little faster to compute.
95 :param patchSize: size of the patch used by the oriented BRIEF descriptor. Of course, on smaller pyramid layers the perceived image area covered by a feature will be larger.
99 Finds keypoints in an image and computes their descriptors
101 .. ocv:function:: void ORB::operator()(InputArray image, InputArray mask, vector<KeyPoint>& keypoints, OutputArray descriptors, bool useProvidedKeypoints=false ) const
103 .. ocv:pyfunction:: cv2.ORB.detect(image[, mask]) -> keypoints
104 .. ocv:pyfunction:: cv2.ORB.compute(image, keypoints[, descriptors]) -> keypoints, descriptors
105 .. ocv:pyfunction:: cv2.ORB.detectAndCompute(image, mask[, descriptors[, useProvidedKeypoints]]) -> keypoints, descriptors
108 :param image: The input 8-bit grayscale image.
110 :param mask: The operation mask.
112 :param keypoints: The output vector of keypoints.
114 :param descriptors: The output descriptors. Pass ``cv::noArray()`` if you do not need it.
116 :param useProvidedKeypoints: If it is true, then the method will use the provided vector of keypoints instead of detecting them.
121 .. ocv:class:: BRISK : public Feature2D
123 Class implementing the BRISK keypoint detector and descriptor extractor, described in [LCS11]_.
125 .. [LCS11] Stefan Leutenegger, Margarita Chli and Roland Siegwart: BRISK: Binary Robust Invariant Scalable Keypoints. ICCV 2011: 2548-2555.
129 The BRISK constructor
131 .. ocv:function:: BRISK::BRISK(int thresh=30, int octaves=3, float patternScale=1.0f)
133 .. ocv:pyfunction:: cv2.BRISK([, thresh[, octaves[, patternScale]]]) -> <BRISK object>
135 :param thresh: FAST/AGAST detection threshold score.
137 :param octaves: detection octaves. Use 0 to do single scale.
139 :param patternScale: apply this scale to the pattern used for sampling the neighbourhood of a keypoint.
143 The BRISK constructor for a custom pattern
145 .. ocv:function:: BRISK::BRISK(std::vector<float> &radiusList, std::vector<int> &numberList, float dMax=5.85f, float dMin=8.2f, std::vector<int> indexChange=std::vector<int>())
147 .. ocv:pyfunction:: cv2.BRISK(radiusList, numberList[, dMax[, dMin[, indexChange]]]) -> <BRISK object>
149 :param radiusList: defines the radii (in pixels) where the samples around a keypoint are taken (for keypoint scale 1).
151 :param numberList: defines the number of sampling points on the sampling circle. Must be the same size as radiusList..
153 :param dMax: threshold for the short pairings used for descriptor formation (in pixels for keypoint scale 1).
155 :param dMin: threshold for the long pairings used for orientation determination (in pixels for keypoint scale 1).
157 :param indexChanges: index remapping of the bits.
161 Finds keypoints in an image and computes their descriptors
163 .. ocv:function:: void BRISK::operator()(InputArray image, InputArray mask, vector<KeyPoint>& keypoints, OutputArray descriptors, bool useProvidedKeypoints=false ) const
165 .. ocv:pyfunction:: cv2.BRISK.detect(image[, mask]) -> keypoints
166 .. ocv:pyfunction:: cv2.BRISK.compute(image, keypoints[, descriptors]) -> keypoints, descriptors
167 .. ocv:pyfunction:: cv2.BRISK.detectAndCompute(image, mask[, descriptors[, useProvidedKeypoints]]) -> keypoints, descriptors
169 :param image: The input 8-bit grayscale image.
171 :param mask: The operation mask.
173 :param keypoints: The output vector of keypoints.
175 :param descriptors: The output descriptors. Pass ``cv::noArray()`` if you do not need it.
177 :param useProvidedKeypoints: If it is true, then the method will use the provided vector of keypoints instead of detecting them.
181 .. ocv:class:: KAZE : public Feature2D
183 Class implementing the KAZE keypoint detector and descriptor extractor, described in [ABD12]_. ::
185 class CV_EXPORTS_W KAZE : public Feature2D
189 CV_WRAP explicit KAZE(bool extended, bool upright, float threshold = 0.001f,
190 int octaves = 4, int sublevels = 4, int diffusivity = DIFF_PM_G2);
193 .. note:: AKAZE descriptor can only be used with KAZE or AKAZE keypoints
195 .. [ABD12] KAZE Features. Pablo F. Alcantarilla, Adrien Bartoli and Andrew J. Davison. In European Conference on Computer Vision (ECCV), Fiorenze, Italy, October 2012.
201 .. ocv:function:: KAZE::KAZE(bool extended, bool upright, float threshold, int octaves, int sublevels, int diffusivity)
203 :param extended: Set to enable extraction of extended (128-byte) descriptor.
204 :param upright: Set to enable use of upright descriptors (non rotation-invariant).
205 :param threshold: Detector response threshold to accept point
206 :param octaves: Maximum octave evolution of the image
207 :param sublevels: Default number of sublevels per scale level
208 :param diffusivity: Diffusivity type. DIFF_PM_G1, DIFF_PM_G2, DIFF_WEICKERT or DIFF_CHARBONNIER
212 .. ocv:class:: AKAZE : public Feature2D
214 Class implementing the AKAZE keypoint detector and descriptor extractor, described in [ANB13]_. ::
216 class CV_EXPORTS_W AKAZE : public Feature2D
220 CV_WRAP explicit AKAZE(int descriptor_type, int descriptor_size = 0, int descriptor_channels = 3,
221 float threshold = 0.001f, int octaves = 4, int sublevels = 4, int diffusivity = DIFF_PM_G2);
224 .. note:: AKAZE descriptors can only be used with KAZE or AKAZE keypoints. Try to avoid using *extract* and *detect* instead of *operator()* due to performance reasons.
226 .. [ANB13] Fast Explicit Diffusion for Accelerated Features in Nonlinear Scale Spaces. Pablo F. Alcantarilla, Jesús Nuevo and Adrien Bartoli. In British Machine Vision Conference (BMVC), Bristol, UK, September 2013.
230 The AKAZE constructor
232 .. ocv:function:: AKAZE::AKAZE(int descriptor_type, int descriptor_size, int descriptor_channels, float threshold, int octaves, int sublevels, int diffusivity)
234 :param descriptor_type: Type of the extracted descriptor: DESCRIPTOR_KAZE, DESCRIPTOR_KAZE_UPRIGHT, DESCRIPTOR_MLDB or DESCRIPTOR_MLDB_UPRIGHT.
235 :param descriptor_size: Size of the descriptor in bits. 0 -> Full size
236 :param descriptor_channels: Number of channels in the descriptor (1, 2, 3)
237 :param threshold: Detector response threshold to accept point
238 :param octaves: Maximum octave evolution of the image
239 :param sublevels: Default number of sublevels per scale level
240 :param diffusivity: Diffusivity type. DIFF_PM_G1, DIFF_PM_G2, DIFF_WEICKERT or DIFF_CHARBONNIER
245 .. ocv:class:: SIFT : public Feature2D
247 The SIFT algorithm has been moved to opencv_contrib/xfeatures2d module.