2014-01-31 06:21:52 -0600 | answered a question | Detect if object present in image | how to detect whether an object is found? 1) The size of the good matches is good start point. 2) Typically > 7-8 good matches means that you found the object. |
2014-01-29 22:06:54 -0600 | answered a question | Algorithm used in Descriptor Matcher trainer in OpenCV The implementation of train method for Brute Force Matcher is empty. It only makes sense for other matcher where you can train in advance without query descriptors. |
2014-01-24 11:19:07 -0600 | answered a question | What is the best method to train objects on wall Try this link: link It is really helpful for CascadeClassifier. |
2014-01-24 09:53:30 -0600 | answered a question | Superresolution: error superRes->set("opticalFlow", of); I supposed that If it still do not work, can you provide the whole error message (access conflict)? |
2014-01-24 08:58:37 -0600 | received badge | ● Teacher (source) |
2014-01-24 07:40:29 -0600 | answered a question | OpenCV 2.4.8 cannot load cascade is working fine on my side with the same configuration. |
2014-01-23 09:38:00 -0600 | answered a question | finding image coordinate from contour Did you try: cout << "Point(x,y)=" << contours[i][j].x << "," << contours[i][j].y << endl; |
2014-01-22 08:44:25 -0600 | commented question | Super Resolution with 2.4.8: real time processing? I gave this code example because I wondered if there are other errors but I did not know that this algorithm cannot do real time processing as I wrote it. I saw it afterwards on this forum. However I wonder if other algorithms can be used for Real Time processing. And what is a reasonable maximum resolution for it? |
2014-01-22 05:27:08 -0600 | received badge | ● Editor (source) |
2014-01-22 05:26:35 -0600 | asked a question | Super Resolution with 2.4.8: real time processing? Hi, I have read few other questions about Super Resolution and Video on this forum. But I did not find any tip about real time processing with super resolution. I wanted to test with a webcam but it seems that the algorithms, at least the BTV SuperResolution algorithm, need too many resources to be achieved real time and are supposed to have small input size.
Code: And I call the following part in an infinite loop of a thread and use newRawImage: |