<< imdetect_MSER Feature Detection, Description and Matching imdetect_SIFT >>

IPCV >> Feature Detection, Description and Matching > imdetect_ORB

imdetect_ORB

Detect features from an image with ORB algorithm

Syntax

fobj = imdetect_ORB(im [,nfeatures [,scaleFactor [,nlevels [,edgeThreshold [,firstLevel [,WTA_K [,scoreType [,patchSize]]]]]]]]);

Parameters

im :

Input image

nfeatures:

The maximum number of features to returned. Default value is 500.

scaleFactor :

Pyramid decimation ratio, greater than 1. Default value is 1.2.

nlevels :

The number of pyramid levels. Default value is 8.

edgeThreshold :

This is size of the border where the features are not detected. It should roughly match the patchSize parameter. Default value is 31.

firstLevel :

It should be 0 in the current implementation. Default value is 0.

WTA_K :

The number of points that produce each element of the oriented BRIEF descriptor. Default value is 2.

scoreType :

The default HARRIS_SCORE means that Harris algorithm is used to rank features. Default value is 0.

patchSize :

size of the patch used by the oriented BRIEF descriptor. Default value is 31.

fobj :

Features object contains following fields -

type :

Type of features

n :

Numbers of detected features

x :

Coordinates of the detected features - X

y :

Coordinates of the detected features - Y

size :

Size of detected features

angle :

keypoint orientation

response :

The response by which the most strong keypoints have been selected.

octave :

pyramid octave in which the keypoint has been detected

class_id :

object id

Description

This function used to detect the features of an image using ORB method

Examples

S = imcreatechecker(8,8,[1 0.5]);
fobj = imdetect_ORB(S);
imshow(S); plotfeature(fobj);

See also

Authors

Bibliography

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.


Report an issue
<< imdetect_MSER Feature Detection, Description and Matching imdetect_SIFT >>