Ask Your Question

Koen Wildemeersch's profile - activity

2017-11-29 03:29:38 -0500 received badge  Notable Question (source)
2016-12-27 12:11:05 -0500 received badge  Famous Question (source)
2016-11-15 10:46:08 -0500 received badge  Popular Question (source)
2016-03-30 23:25:22 -0500 received badge  Notable Question (source)
2015-08-17 06:34:42 -0500 received badge  Popular Question (source)
2013-12-31 08:13:19 -0500 received badge  Student (source)
2013-12-28 07:34:29 -0500 asked a question feature detector key point to contour

Hi all,

I'm wondering about the following. Using cv2.mser() one can choose to obtain key points or contours. I'm interested in the contour only (looking for blobs, not to compare with other images).

Using the following method (see below) one can also apply mser, only to obtain key points so it seems. Is there a way to use these key points to get the contours of the blobs? The reason I ask is because I would like to see that blobs are detected using the different feature detectors. (Note: As far as I'm aware feature detectors aren't usually used to derive blobs, but nevertheless I wanted to ask this question).

forb = cv2.FeatureDetector_create(...) kpts = forb.detect(...)

Kind regards, Koen

2013-12-28 05:06:07 -0500 asked a question HOW TO: mser constructor with algorithm parameters (python)

Hi all,

I've noticed that using C++ it is possible to set the algorithm parameters when constructing the object. (see: http://docs.opencv.org/modules/features2d/doc/feature_detection_and_description.html?highlight=mser#MSER : public FeatureDetector)

I do not succeed to do the same in python (see code below). The object is constructed without errors, but I can't see the properties, nor modify them or set them manually. Any ideas? Btw, I'm using this mser method because it returns me the contours and not only the key points.

_delta = 10 
_min_area = 25 
_max_area = 2000
_max_variation = 10.0 
_min_diversity = 10.0
_max_evolution = 10 
_area_threshold = 12.0
_min_margin = 2.9 
_edge_blur_size = 3    

mser2 = cv2.MSER(_delta,_min_area,_max_area,
      _max_variation, _min_diversity,
      _max_evolution, _area_threshold,
      _min_margin, _edge_blur_size )

Best of wishes for 2014!

Kind regards, Koen

2013-12-28 04:31:07 -0500 received badge  Scholar (source)
2013-08-17 06:37:36 -0500 asked a question How to use MSER in Python

Hi all, I've used MSER from VLfeat toolbox (matlab) and noticed that open cv also has they same method available. From my search on this Q&A I'm sure it's available for C++ but I'm not sure if I can use in in python as well. Could anyone help me on this one? If it's possible, could you provide me with an example as I found nothing in the documentation.

Thank you very much!

Koen