2015-09-06 16:22:54 -0600 | received badge | ● Enthusiast |
2015-09-05 08:47:12 -0600 | received badge | ● Self-Learner (source) |
2015-09-05 08:44:49 -0600 | answered a question | Is this expected HOG outcome? That problem seems to be known for quite a while. http://code.opencv.org/issues/4149 As mentioned in the code there is an assertion for accessing rows out of a submatrix.(hog.cpp, 311+). The code might still access values out of the submatrix range in x direction. Anyway the result is different gradient image output in x direction. computeGradient of ROI(isContinious = false; isSubmatrix = true) outputs following gradImg: ROI_clone(isContinious = true; isSubmatrix = false): |
2015-09-04 07:16:32 -0600 | commented answer | Is this expected HOG outcome? Found the answer to "why" has to do with submatrices and the resulting gradient image. I will post an extended version. 48 hour answer block ;) |
2015-09-03 09:08:17 -0600 | received badge | ● Student (source) |
2015-09-03 05:06:15 -0600 | asked a question | Is this expected HOG outcome? Hi, HOGDescriptor::compute() somehow does not behave as expected for me. It generates different output for the same window(see code). Is there a explanation for? Mat imgRaw = imread("...", 1); |