skimage2.feature.ORB#

class skimage2.feature.ORB(downscale=1.2, n_scales=8, n_keypoints=500, fast_n=9, fast_threshold=0.08, harris_k=0.04)[source]#

Bases: FeatureDetector, DescriptorExtractor

Oriented FAST and rotated BRIEF feature detector and binary descriptor extractor.

Parameters:

n_keypointsint, optional: Number of keypoints to be returned. The function will return the best n_keypoints according to the Harris corner response if more than n_keypoints are detected. If not, then all the detected keypoints are returned.
fast_nint, optional: The n parameter in skimage.feature.corner_fast. Minimum number of consecutive pixels out of 16 pixels on the circle that should all be either brighter or darker w.r.t test-pixel. A point c on the circle is darker w.r.t test pixel p if Ic < Ip - threshold and brighter if Ic > Ip + threshold. Also stands for the n in FAST-n corner detector.
fast_thresholdfloat, optional: The threshold parameter in feature.corner_fast. Threshold used to decide whether the pixels on the circle are brighter, darker or similar w.r.t. the test pixel. Decrease the threshold when more corners are desired and vice-versa.
harris_kfloat, optional: The k parameter in skimage.feature.corner_harris. Sensitivity factor to separate corners from edges, typically in range [0, 0.2]. Small values of k result in detection of sharp corners.
downscalefloat, optional: Downscale factor for the image pyramid. Default value 1.2 is chosen so that there are more dense scales which enable robust scale invariance for a subsequent feature description.
n_scalesint, optional: Maximum number of scales from the bottom of the image pyramid to extract the features from.

Attributes:

keypointsndarray of shape (N, 2): Keypoint coordinates as (row, col).
scalesndarray of shape (N,): Corresponding scales.
orientationsndarray of shape (N,): Corresponding orientations in radians.
responsesndarray of shape (N,): Corresponding Harris corner responses.
descriptorsndarray of shape (Q, descriptor_size) and dtype bool: 2D array of binary descriptors of size descriptor_size for Q keypoints after filtering out border keypoints with value at an index (i, j) either being True or False representing the outcome of the intensity comparison for i-th keypoint on j-th decision pixel-pair. It is Q == np.sum(mask).

References

[1]

Ethan Rublee, Vincent Rabaud, Kurt Konolige and Gary Bradski “ORB: An efficient alternative to SIFT and SURF” http://www.vision.cs.chubu.ac.jp/CV-R/pdf/Rublee_iccv2011.pdf

Examples

>>> from _skimage2.feature import ORB, match_descriptors
>>> img1 = np.zeros((100, 100))
>>> img2 = np.zeros_like(img1)
>>> rng = np.random.default_rng(19481137)  # do not copy this value
>>> square = rng.random((20, 20))
>>> img1[40:60, 40:60] = square
>>> img2[53:73, 53:73] = square
>>> detector_extractor1 = ORB(n_keypoints=5)
>>> detector_extractor2 = ORB(n_keypoints=5)
>>> detector_extractor1.detect_and_extract(img1)
>>> detector_extractor2.detect_and_extract(img2)
>>> matches = match_descriptors(detector_extractor1.descriptors,
...                             detector_extractor2.descriptors)
>>> matches
array([[0, 0],
       [1, 1],
       [2, 2],
       [3, 4],
       [4, 3]])
>>> detector_extractor1.keypoints[matches[:, 0]]
array([[59. , 59. ],
       [40. , 40. ],
       [57. , 40. ],
       [46. , 58. ],
       [58.8, 58.8]])
>>> detector_extractor2.keypoints[matches[:, 1]]
array([[72., 72.],
       [53., 53.],
       [70., 53.],
       [59., 71.],
       [72., 72.]])

__init__(downscale=1.2, n_scales=8, n_keypoints=500, fast_n=9, fast_threshold=0.08, harris_k=0.04)[source]#

detect(image)[source]#

Detect oriented FAST keypoints along with the corresponding scale.

Parameters:

image2D array: Input image.

detect_and_extract(image)[source]#

Detect oriented FAST keypoints and extract rBRIEF descriptors.

Note that this is faster than first calling detect and then extract.

Parameters:

image2D array: Input image.

extract(image, keypoints, scales, orientations)[source]#

Extract rBRIEF binary descriptors for given keypoints in image.

Note that the keypoints must be extracted using the same downscale and n_scales parameters. Additionally, if you want to extract both keypoints and descriptors you should use the faster detect_and_extract.

Parameters:

imagendarray of shape (K, L): Input image.
keypointsndarray of shape (N, 2): Keypoint coordinates as (row, col).
scalesndarray of shape (N,): Corresponding scales.
orientationsndarray of shape (N,): Corresponding orientations in radians.