Evaluates a feature detector

[repeatability, correspCount] = cv.evaluateFeatureDetector(img1, img2, H1to2, keypoints1, keypoints2)
[...] = cv.evaluateFeatureDetector(..., 'OptionName',optionValue, ...)

Input

• img1 First image.
• img2 Second image.
• H1to2 3x3 double matrix. Homography relating img1 to img2.
• keypoints1 Keypoints detected in img1
• keypoints2 Keypoints detected in img2

Output

• repeatability Repeatability (float value), between 0.0 and 1.0
• correspCount Correspondences count (int value).

Options

• Detector feature detector that finds keypoints in images. It can be specified as a string containing the type of feature detector, such as 'ORB'. It can also be specified as a cell-array of the form {fdetector, 'key',val, ...}, where the first element is the type, and the remaining elements are optional parameters used to construct the specified feature detector. See cv.FeatureDetector for possible types. Not set by default (i.e: you must supply pre-detected keypoints in the inputs).

Example

detector = cv.FeatureDetector('SURF');
kp1 = detector.detect(img1)
kp2 = detector.detect(img2)
[rep,corresp] = cv.evaluateFeatureDetector(img1, img2, H1to2, kp1, kp2)