Geek Answers Handbook

Blobs with OpenCV. Which library is better?

I plan to start experimenting with blobs as a C ++ user, with some experience with cv :: Mat from OpenCV.

Now the question is, which blobs library should I use, if at all?

I have seen these alternatives so far:

  • cvBlobs (in google code) is really an ac library working with IplImage, so a serious adaptation to C ++ is needed.
  • CvBlobsLib (on the opowv weowgarage web page ) - it looks like a C ++ library, but it has pretty bad documents with a lot of unnecessary materials and hardly any code sample.
  • I saw cv :: findContours, cv :: moments and cv :: drawContours in the OpenCV 2.4.3 library.

What do you offer as an expert? My pressing issue: that the new OpenCV will not close cvBlobs in google code?

Here is the link to the next question on this, where I ask about SimpleBlobDetector . You may be interested.

+6
source share
2 answers

You should use the SimpleBlobDetector class in OpenCV 2.4. You pretty much create an object of type SimpleBlobDetector , and then call the detect(cv::Mat input, vector<cv::KeyPoint> keypoints, cv::Mat mask) function detect(cv::Mat input, vector<cv::KeyPoint> keypoints, cv::Mat mask) using the cv :: Mat image as input, an empty vector for key points and another cv :: Mat as an additional mask for a specific area of ​​the image to search for key points.

Note that the cv :: Mat object took over the processing of images and memory for all previously separated image and matrix classes in earlier versions of OpenCV.

+5
source

You should take a look at the new opencvblobslib . It has great features like multi-core processor support.

+2
source

More articles:


All Articles