Computer vision functions (FAST, ORB, etc)
arrayfire.vision.dog(image, radius1, radius2)[source]¶
Difference of gaussians.
A 2D array specifying an image.
The radius of first gaussian kernel.
The radius of second gaussian kernel.
A multi dimensional array containing the difference of gaussians.
arrayfire.vision.fast(image, threshold=20.0, arc_length=9, non_max=True, feature_ratio=0.05, edge=3)[source]¶
FAST feature detector.
A 2D array representing an image.
FAST threshold for which a pixel of the circle around a central pixel is consdered.
The minimum length of arc length to be considered. Max length should be 16.
A boolean flag specifying if non max suppression has to be performed.
Specifies the maximum ratio of features to pixels in the image.
Specifies the number of edge rows and columns to be ignored.
Contains the location and score. Orientation and size are not computed.
arrayfire.vision.gloh(image, num_layers=3, contrast_threshold=0.04, edge_threshold=10.0, initial_sigma=1.6, double_input=True, intensity_scale=0.00390625, feature_ratio=0.05)[source]¶
GLOH feature detector and descriptor.
A 2D array representing an image
Number of layers per octave. The number of octaves is calculated internally.
Threshold used to filter out features that have low contrast.
Threshold used to filter out features that are too edge-like.
The sigma value used to filter the input image at the first octave.
If True, the input image will be scaled to double the size for the first octave.
The inverse of the difference between maximum and minimum intensity values.
Specifies the maximum number of features to detect as a ratio of image pixels.
descriptor is an af.Array of size N x 272
arrayfire.vision.hamming_matcher(query, database, dim=0, num_nearest=1)[source]¶
Hamming distance matcher.
A query feature descriptor
A multi dimensional array containing the feature descriptor database.
Specifies the dimension along which feature descriptor lies.
Specifies the number of nearest neighbors to find.
location and distances of closest matches.
arrayfire.vision.harris(image, max_corners=500, min_response=100000.0, sigma=1.0, block_size=0, k_thr=0.04)[source]¶
Harris corner detector.
A 2D array specifying an image.
Specifies the maximum number of corners to be calculated.
Specifies the cutoff score for a corner to be considered
Specifies the standard deviation of a circular window.
Only used when block_size == 0. Must be >= 0.5 and <= 5.0.
Specifies the window size.
Harris constant. must be >= 0.01
Contains the location and score. Orientation and size are not computed.
arrayfire.vision.homography(x_src, y_src, x_dst, y_dst, htype=<HOMOGRAPHY.RANSAC: 0>, ransac_threshold=3.0, iters=1000, out_type=<Dtype.f32: 0>)[source]¶
Homography estimation
A list of x co-ordinates of the source points.
A list of y co-ordinates of the source points.
A list of x co-ordinates of the destination points.
A list of y co-ordinates of the destination points.
HOMOGRAPHY.RANSAC: RANdom SAmple Consensus will be used to evaluate quality.
HOMOGRAPHY.LMEDS : Least MEDian of Squares is used to evaluate quality.
If htype is HOMOGRAPHY.RANSAC, it specifies the L2-distance threshold for inliers.
Specifies the output data type.
arrayfire.vision.match_template(image, template, match_type=<MATCH.SAD: 0>)[source]¶
Find the closest match of a template in an image.
A multi dimensional array specifying an image or batch of images.
A multi dimensional array specifying a template or batch of templates.
Specifies the match function metric.
An array containing the score of the match at each pixel.
arrayfire.vision.nearest_neighbour(query, database, dim=0, num_nearest=1, match_type=<MATCH.SSD: 3>)[source]¶
Nearest Neighbour matcher.
A query feature descriptor
A multi dimensional array containing the feature descriptor database.
Specifies the dimension along which feature descriptor lies.
Specifies the number of nearest neighbors to find.
Specifies the match function metric.
location and distances of closest matches.
arrayfire.vision.orb(image, threshold=20.0, max_features=400, scale=1.5, num_levels=4, blur_image=False)[source]¶
ORB Feature descriptor.
A 2D array representing an image.
FAST threshold for which a pixel of the circle around a central pixel is consdered.
Specifies the maximum number of features to be considered.
Specifies the factor by which images are down scaled at each level.
Specifies the number of levels used in the image pyramid.
Flag specifying if the input has to be blurred before computing descriptors. A gaussian filter with sigma = 2 is applied if True.
descriptor is an af.Array of size N x 8
arrayfire.vision.sift(image, num_layers=3, contrast_threshold=0.04, edge_threshold=10.0, initial_sigma=1.6, double_input=True, intensity_scale=0.00390625, feature_ratio=0.05)[source]¶
SIFT feature detector and descriptor.
A 2D array representing an image
Number of layers per octave. The number of octaves is calculated internally.
Threshold used to filter out features that have low contrast.
Threshold used to filter out features that are too edge-like.
The sigma value used to filter the input image at the first octave.
If True, the input image will be scaled to double the size for the first octave.
The inverse of the difference between maximum and minimum intensity values.
Specifies the maximum number of features to detect as a ratio of image pixels.
descriptor is an af.Array of size N x 128
arrayfire.vision.susan(image, radius=3, diff_thr=32, geom_thr=10, feature_ratio=0.05, edge=3)[source]¶
SUSAN corner detector.
A 2D array specifying an image.
Specifies the radius of each pixel neighborhood.
Specifies the intensity difference threshold.
Specifies the geometric threshold.
Specifies the ratio of corners found to number of pixels.
Specifies the number of edge rows and columns that are ignored.
Contains the location and score. Orientation and size are not computed.
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4