2017-08-22 16:22:15 -0600 | received badge | ● Nice Answer (source) |
2017-04-04 07:50:50 -0600 | received badge | ● Teacher (source) |
2017-04-04 03:39:12 -0600 | received badge | ● Self-Learner (source) |
2017-04-04 03:02:10 -0600 | answered a question | Downhill Solver -- error due to pure virtual functions thanks berak. I will post my small code as an hint for those, like me, are novice to opencv. I'm using opencv with qt on a win10 machine, compiling with mingw. |
2017-03-30 07:05:23 -0600 | received badge | ● Student (source) |
2017-03-30 04:33:23 -0600 | commented answer | Downhill Solver -- error due to pure virtual functions Thank you, Berak. the code is now working. couldnt post it as a comment since it's too long. btw, I'm using opencv 3.0.0 with qt and mingw as a compiler on a win10 machine |
2017-03-30 03:44:44 -0600 | received badge | ● Editor (source) |
2017-03-30 03:29:52 -0600 | asked a question | Downhill Solver -- error due to pure virtual functions I'm familiarizing with Optimization Algorithm in OpenCV. I've found an interesting example to start with: http://answers.opencv.org/question/33... so, I developed some code based on that: It gives me the following error, when building: any hint? I saw that there are not many examples on the web about these methods, so I cannot figure out what is happening. |
2017-03-29 06:32:38 -0600 | commented answer | getting score and raw data of each circle with CvHoughCircles sorry for the post, did not notice the policy you are talking about; I'll remove the answer if you prefer. btw, why this huge downvote? is there something wrong? the code i've posted works nicely for me. |
2017-03-29 05:33:49 -0600 | answered a question | getting score and raw data of each circle with CvHoughCircles I eventually found an answer.
if you get into the code (the function is ' hope this helps, Guido. |
2017-03-09 07:05:31 -0600 | commented answer | Possible BUG in denoise_TVL1 Indeed, the problem was with the input argument, I did not understand that a vector<mat> rather than a Mat was needed. Thanks and sorry for the double post. |
2017-03-09 05:58:01 -0600 | commented answer | Possible BUG in denoise_TVL1 I've tried with several images, but of the same type. jpg in grayscale |
2017-03-09 05:09:10 -0600 | asked a question | Possible BUG in denoise_TVL1 I re-ask the question since I didnt found help with that. I'm pretty about to post it in the BUG section, if still nobody has any clue. I would like to denoise a grayscale image using the TV regularization, in order to prevent sharp edges being smoothed out. I'm working in win10 with Qt 5.4.1, mingw compiler and OpenCV 3.0. I tried the aforementioned algorithm but this gives me the following error: OpenCV Error: Assertion failed ((flags & FIXED_TYPE) != 0) in type, file C:\opencv\sources\modules\core\src\matrix.cpp, line 1821 seems like a type error, but it looks strange to me since I'm just loading a grayscale image. please note that the function 'fastNlMeansDenoising' works flawlessly within the same framework. For better clarity, here's the pseudo code: thank you for your help, Guido. |
2017-03-06 02:58:29 -0600 | commented question | denoise_TVL1 not working? still could not believe no-one is giving any hint. is this question so trivial? |
2017-03-06 02:55:02 -0600 | commented question | How to use my HOG matrix in the SVM classifier? you've already trained your svm when typing: you don't need to train it another time |
2017-03-03 10:40:35 -0600 | commented question | How to use my HOG matrix in the SVM classifier? the .xml file contains the trained SVM data you'll use for prediction (i.e. support vectors, margin, etc...); try to open it with a txt editor to see that. once you have it, just use it for prediction (svm->predict...); it is meaningless to re-train another svm using the .xml as you did. |
2017-03-03 09:02:23 -0600 | commented question | How to use my HOG matrix in the SVM classifier? something like:
Ptr<ml::svm> svm = ml::SVM::load<cv::ml::svm>(yourSVMfilename);
HOGd.compute(yourImage, descriptorsValues);
previsionLabel = svm->predict(descriptorsValues, noArray(), 0); is it helpful? |
2017-03-03 05:04:25 -0600 | commented question | How to use my HOG matrix in the SVM classifier? it seems your code is training then saving your svm classifier.
once you have your .xml file you just have to load it and then use
|
2017-03-03 02:33:45 -0600 | received badge | ● Enthusiast |
2017-03-02 05:36:48 -0600 | commented question | denoise_TVL1 not working? any clue? I think variational denoising (especially using the L1 gradient norm) is quite important in the field of image treatment... |
2017-03-01 08:18:12 -0600 | commented question | denoise_TVL1 not working? forget to say: my compiler is mingw... |
2017-03-01 05:16:28 -0600 | asked a question | denoise_TVL1 not working? I would like to denoise a grayscale image using the TV regularization, in order to prevent sharp edges being smoothed out. I'm working in win10 with Qt 5.4.1 and OpenCV 3.0. I tried the aforementioned algorithm but this gives me the following error: OpenCV Error: Assertion failed ((flags & FIXED_TYPE) != 0) in type, file C:\opencv\sources\modules\core\src\matrix.cpp, line 1821 seems like a type error, but it looks strange to me since I'm just loading a grayscale image. please note that the function 'fastNlMeansDenoising' works flawlessly within the same framework. For better clarity, here's the pseudo code: any hint? thank you, Guido. |
2017-01-04 02:36:11 -0600 | commented question | Quadratic Programming in OpenCV 3.0.0 Thanks Lorena. I looked at the new opencv release doc you suggested but still there's no QP. thanks also for the link to the code, which is very interesting although indeed quite taylored on svm kind of 'Q matrices' and therefore not very useful for me. |
2017-01-03 09:57:46 -0600 | asked a question | Quadratic Programming in OpenCV 3.0.0 I'm recently trying to solve a problem which involves quadratic (semi-definite) programming in C++. since I sometimes use OpenCV library and I'm aware that SVM is indeed supported, I'm rather astonished that in this page: http://docs.opencv.org/3.0-beta/modul... no stuff for solving QP pbs is provided. Am I wrong? How a SVM could be trained without using QP's methods? Many thanks for your kind answers. Guido |
2016-10-21 02:47:22 -0600 | commented question | Stitching two fisheye images in order to undistort, you would perhaps try hough circles transform to find the outer contour and then use linear-polar to rectify, given the aforementioned circle. (chouette! c'est le palais royal à Paris!) |
2016-10-18 05:16:34 -0600 | commented question | Where to start with pattern recognition try with generalized hough transform if the shape is reasonably known or match feature beetween images with kaze or similar. |
2016-10-11 02:33:02 -0600 | commented answer | How to initialize a Mat object with zeros thanks for the editing! |
2016-10-11 02:16:45 -0600 | answered a question | How to initialize a Mat object with zeros for a grayscale image this should work (works for me, I use openCV 3.0): where n_rows and n_cols are the number of rows and colums (thus, int) respectively. if your image is not grayscale, change the last entry. |