<< imdetect_ORB Feature Detection, Description and Matching imdetect_STAR >>

IPCV - Image Processing and Computer Vision Toolbox for Scilab >> Feature Detection, Description and Matching > imdetect_SIFT

imdetect_SIFT

Detect features from an image with SIFT algorithm

Syntax

fobj = imdetect_SIFT(im [,nfeatures [,nOctaveLayers [,contrastThreshold [,edgeThreshold [,sigma]]]]])

Parameters

im :

Input image

nfeatures :

The number of best features to retain. The features are ranked by their scores. Default value is 0.

nOctaveLayers :

The number of layers in each octave. Default value is 3.

contrastThreshold :

The contrast threshold used to filter out weak features in semi-uniform (low-contrast) regions. Default value is 0.04.

edgeThreshold :

The threshold used to filter out edge-like features. Default value is 10.

sigma :

The sigma of the Gaussian applied to the input image at the octave #0. Default value is 1.6.

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 SIFT method

Examples

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

See also

Authors

Bibliography

1. OpenCV 2.4 Online Documentation


Report an issue
<< imdetect_ORB Feature Detection, Description and Matching imdetect_STAR >>