Ask Your Question

slycheese's profile - activity

2015-10-25 23:51:17 -0500 commented answer Face detect inconsistent performance

@StevenPuttemans Can you offer any advice on how one should select the stepsize in the image pyramid given a particular resolution input image?

For reference, the reason I'm changing the search ROI is because once I find where the face is in the relatively large input image, on subsequent frames I want to only search in a smaller ROI where the face was previously found (since it's unlikely that it moved very far in one frame). This seems like something that would be a fairly common practice.

2015-10-23 02:39:01 -0500 received badge  Student (source)
2015-10-23 02:10:13 -0500 commented question Face detect inconsistent performance

@LorenaGdL Because I didn't know that there was a new release out. Thanks, I'll give that a try.

2015-10-22 17:52:53 -0500 commented question Face detect inconsistent performance

@LorenaGdL Thanks for testing the image, I appreciate that. I've edited my post again to include the backtrace from the seg fault that I get when I try to use that image. Unfortunately, disabling the eye detection phase didn't help. Disabling the call to the cascade classifier does make the seg fault stop (as the backtrace suggests it would). So I guess we know there isn't an issue with loading the image file.

@StevenPuttemans I've updated the program (included in this post) so that it adjusts the face search ROI. It doesn't find the face for any size ROI (at least of the ones I've tried) in my original test image. I just downloaded 10 "randomly" selected images via a Google search and they all caused seg faults, so I guess that needs to be sorted out before I can do much more testin

2015-10-22 17:04:11 -0500 commented question Face detect inconsistent performance

@LorenaGdL I've added a sample image to my problem description that causes a seg fault. Regarding the distortion my test image, you are right, it has some distortion, but when using the old interface to the cascade classifier it is able to find the face, so it doesn't make sense to me that the new interface would return a different result.

2015-10-22 13:23:40 -0500 commented question Face detect inconsistent performance

@StevenPuttemans With this new sample program I have not yet tried modifying the face search ROI. I stopped short of that because the program seg faults with some test images. That indicates a pretty serious problem, so I didn't think it made sense to put in all the varied-size ROI test code before checking back here.

2015-10-22 13:20:04 -0500 commented question Face detect inconsistent performance

@LorenaGdL 1. I did hardcode the image filename at first; I added the command-line parse after, for convenience. 2. It's not a problem parsing the file because the image displays in the OpenCV window, as it should, but no face is detected.

2015-10-21 19:59:08 -0500 commented question Face detect inconsistent performance

@LorenaGdL @StevenPuttemans I grabbed the new objectDetection.cpp sample code and started to modify it, but I found that it can't detect the face in my test image (same one I've been using this I started this thread). I've also found that the program seg faults with some other images. I've update the original post to reflect this, and you can find my modified code there.

2015-10-13 14:28:17 -0500 commented question Face detect inconsistent performance

@LorenaGdL Thanks, will take a look.

2015-10-13 14:23:45 -0500 commented question Face detect inconsistent performance

@StevenPuttemans I'm not sure what "sample o_O" means, but the code I posted is what's in "samples/cpp/facedetect.cpp" in the 3.0.0 codebase, with my noted modifications.

2015-10-12 23:48:55 -0500 received badge  Editor (source)
2015-10-08 15:28:23 -0500 commented question Face detect inconsistent performance

@LorenaGdL, @StevenPuttemans: I modified the OpenCV example face-detect code to show the issue. Thanks again for your thoughts on this.

2015-10-06 14:13:48 -0500 commented question Face detect inconsistent performance

LorenaGdL:

  • What I meant is that if you take a still photo and run face detection on it using various ROIs (each of which includes the face in its rectangle), for some ROIs the face is found and for others it isn't. I can see no pattern with regard to which ROIs work and which don't. ROIs that work/don't work are coupled with the still photo used, i.e., if you switch and use a different still image, the set of ROIs that work change. When I say "dimensions/position" I mean the size and width of the ROI, and the position of it's top-left corner, and as I said, I can not see a pattern in with locations/sizes of ROI work and with don't.

  • I think that the filter is deterministic, isn't it? If that's the case, then for a ...

(more)
2015-10-03 14:48:31 -0500 asked a question Face detect inconsistent performance

I'm using the cascade classifier with the front-face training data to detect faces in a still image (i.e. static jpg). I don't want to have to search the whole image for faces at once, so I send the cascade classifier an ROI from the full image. What I've found is that the classifier's ability to find the face in the image is dependent on the dimensions/position of the ROI I give it. Note, I only give it ROIs that include the face fully, and with lots of margin.

I'm using OpenCV 3.0.0.

I had modified the OpenCV sample program to demonstrate the behavior, but was then informed that that sample program was old and used an interface to the cascade classifier that is no longer valid. I have modified the new OpenCV sample program (obtained from: http://docs.opencv.org/master/db/d28/...) but that code can't find the face in my sample image at all (see below), which is the same image I have been using all along. I've also found that when I test some other images, the sample program seg faults.

Sample image: C:\fakepath\faceDetectTestImage.png

Sample image that causes seg fault: image description

Backtrace after seg fault:

Program received signal SIGSEGV, Segmentation fault.
0xb7816a42 in cv::CascadeClassifierImpl::runAt(cv::Ptr<cv::FeatureEvaluator>&, cv::Point_<int>, int, double&) ()
   from /home/mss/src/opencv-3.0.0-beta/build/lib/libopencv_objdetect.so.3.0
(gdb) bt
#0  0xb7816a42 in cv::CascadeClassifierImpl::runAt(cv::Ptr<cv::FeatureEvaluator>&, cv::Point_<int>, int, double&) ()
   from /home/mss/src/opencv-3.0.0-beta/build/lib/libopencv_objdetect.so.3.0
#1  0xb781d189 in cv::CascadeClassifierInvoker::operator()(cv::Range const&) const () from /home/mss/src/opencv-3.0.0-beta/build/lib/libopencv_objdetect.so.3.0
#2  0xb7ed12d7 in cv::parallel_for_(cv::Range const&, cv::ParallelLoopBody const&, double) ()
   from /home/mss/src/opencv-3.0.0-beta/build/lib/libopencv_core.so.3.0
#3  0xb781f068 in cv::CascadeClassifierImpl::detectMultiScaleNoGrouping(cv::_InputArray const&, std::vector<cv::Rect_<int>, std::allocator<cv::Rect_<int> > >&, std::vector<int, std::allocator<int> >&, std::vector<double, std::allocator<double> >&, double, cv::Size_<int>, cv::Size_<int>, bool) ()
   from /home/mss/src/opencv-3.0.0-beta/build/lib/libopencv_objdetect.so.3.0
#4  0xb7828956 in cv::CascadeClassifierImpl::detectMultiScale(cv::_InputArray const&, std::vector<cv::Rect_<int>, std::allocator<cv::Rect_<int> > >&, std::vector<int, std::allocator<int> >&, std::vector<double, std::allocator<double> >&, double, int, int, cv::Size_<int>, cv::Size_<int>, bool) ()
   from /home/mss/src/opencv-3.0.0-beta/build/lib/libopencv_objdetect.so.3.0
#5  0xb7812af1 in cv::CascadeClassifierImpl::detectMultiScale(cv::_InputArray const&, std::vector<cv::Rect_<int>, std::allocator<cv::Rect_<int> > >&, double, int, int, cv::Size_<int>, cv::Size_<int>) ()
   from /home/mss/src/opencv-3.0.0-beta/build/lib/libopencv_objdetect.so.3.0
#6  0xb78171a6 in cv::CascadeClassifier::detectMultiScale(cv::_InputArray const&---Type <return> to continue, or q <return> to quit---
, std::vector<cv::Rect_<int>, std::allocator<cv::Rect_<int> > >&, double, int, int ...
(more)
2015-03-16 17:36:29 -0500 asked a question Camera image blurry (but not in Cheese)

I have a USB camera that I'm working with and when I view it via OpenCV (or guvcview) it is quite noticeably blurry. When I view the same camera in Cheese it looks really nice and sharp. Is this something anyone else has run into before? Is there a make-it-blurry camera property that I need to clear? :)

Thanks in advance!

2015-03-16 10:05:00 -0500 received badge  Enthusiast
2015-03-08 03:30:33 -0500 asked a question USB 3 Camera read incorrectly via OpenCV

I have a USB 3 UVC camera. When attached to a USB 3 port I am able to run guvcview and the camera displays properly at all resolutions. When I run OpenCV and try to read from the camera it works fine if I set it to 640x480, but at any resolution higher than that I get back erratic images (the pixels aren't random, but the image looks like a random patchwork of what the true image should look like).

To further confuse matters, when I plug the same camera into a USB 2 port, all resolutions display perfectly fine.

I'd blame the camera, expect that it works fine with guvcview, even when attached to a USB 3 port, so it seems that there is something special about OpenCV that is not allowing it to work properly.

I'd be very grateful for any suggestions/help you can offer.

Thanks, mark

2014-12-03 18:59:29 -0500 received badge  Supporter (source)
2014-12-03 17:01:09 -0500 commented question OpenCV CascadeClassifier Segmentation Fault

I realize this is a year and a half later, but I just wanted to say that I'm having the exact same issue (running Ubuntu 14.04 on Odroid XU3, and I compiled OpenCV for multithreading ((and I'm using the C++ interface to OpenCV)).