Detect features from an image with MSER algorithm
fobj = imdetect_MSER(im [,delta [,min_area [,max_area [,max_variation [,min_diversity [,max_evolution [,area_threshold [,min_margin [,edge_blur_size]]]]]]]]]);
Input image
Compares (sizei - sizei-delta)/sizei-delta. Default value is 5.
Prune the area which smaller than minArea. Default value is 60.
Prune the area which bigger than maxArea. Default value is 14400.
Prune the area have simliar size to its children. Default value is 0.25.
For color image, trace back to cut off mser with diversity less than min_diversity. Default value is 0.2.
For color image, the evolution steps. Default value is 200.
For color image, the area threshold to cause re-initialize. Default value is 1.01.
For color image, ignore too small margin. Default value is 0.003.
For color image, the aperture size for edge blur. Default value is 5.
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 MSER method
1. OpenCV 2.4 Online Documentation