Detect features from an image with ORB algorithm
fobj = imdetect_ORB(im [,nfeatures [,scaleFactor [,nlevels [,edgeThreshold [,firstLevel [,WTA_K [,scoreType [,patchSize]]]]]]]]);
Input image
The maximum number of features to returned. Default value is 500.
Pyramid decimation ratio, greater than 1. Default value is 1.2.
The number of pyramid levels. Default value is 8.
This is size of the border where the features are not detected. It should roughly match the patchSize parameter. Default value is 31.
It should be 0 in the current implementation. Default value is 0.
The number of points that produce each element of the oriented BRIEF descriptor. Default value is 2.
The default HARRIS_SCORE means that Harris algorithm is used to rank features. Default value is 0.
size of the patch used by the oriented BRIEF descriptor. Default value is 31.
Features object contains following fields -
Type of features
Numbers of detected features
Coordinates of the detected features - X
Coordinates of the detected features - Y
Size of detected features
keypoint orientation
The response by which the most strong keypoints have been selected.
pyramid octave in which the keypoint has been detected
object id
This function used to detect the features of an image using ORB method
1. OpenCV 2.4 Online Documentation
2. Ethan Rublee, Vincent Rabaud, Kurt Konolige, Gary R. Bradski: ORB: An efficient alternative to SIFT or SURF. ICCV 2011: 2564-2571.