Ask Your Question

peterl's profile - activity

2015-11-17 12:51:36 -0500 asked a question pose invariant face detection - can this be done?

Is the pose invariant face detection achievable in OpenCV? How one would approach this problem?

2015-11-01 13:05:37 -0500 commented question Where would I see a benefit of running OpenCV on CUDA enabled machine for face detection?

Ok, seems like the code needs to change, and since it is Java, I'm not sure how to access the GPU support of OpenCV, any ideas?

2015-11-01 13:04:39 -0500 answered a question Image Editing Capability using GPU with Java API support

It has been a while since this question was asked. Any changes on this for JAVA API?

2015-11-01 12:49:46 -0500 asked a question Where would I see a benefit of running OpenCV on CUDA enabled machine for face detection?

I have a test that does face blur on a video file. Pretty straightforward, from followed by profile face detection and then a blur of the fund results. It runs on my local machine at 10 times real time speed with scale factor of 1.1 and 15 connected components. I was hopping to see a speed improvement of GPU CUDA enabled instance but the speed is the dame. The OpenCV was build from git source and there were a whole bunch of CUDA modules built.

Should I see an improvement? How can I make sure GPU is utilized?

Thank you!

2015-11-01 12:44:09 -0500 commented answer How to save captured video in java

Yep, clone of master has it, thanks.

2015-11-01 12:43:43 -0500 received badge  Supporter (source)
2015-11-01 12:43:16 -0500 answered a question How to save captured video in java

Yep, clone of master has it, thanks.

2015-10-23 14:19:20 -0500 commented answer How to save captured video in java

The latest version on github is the release of 3.0.0 and that doesn't have VideoWriter component. Is there a particular tag or branch where the VideoWriter is present?

2015-10-23 14:18:53 -0500 answered a question How to save captured video in java

The latest version on github is the release of 3.0.0 and that doesn't have VideoWriter component. Is there a particular tag or branch where the VideoWriter is present?

2015-10-17 20:32:30 -0500 asked a question approach to face detection in video (variable sizes and 3/4 turns)?

Hi All,

I'm wondering if there are any available cascades trained for video? I'm looking for the way to blur multiple faces on a video and struggling with making it work with cascades that come with OpenCV 3.0. The video has variable size faces (closer and farther from the camera) and my first naive attempt was to run the classifier with smallest minimum size and no maximum size to detect all of the faces. That failed meaning there were too many false positives. The second attempt was to do a multi pass with min and max sizes set to detect a certain group of faces on each pass. This is not ideal since it's hard to predict the bounds and obviously takes much more time. Also there is a problem that I couldn't solve with faces that are 3/4 turned, those are not detected by either frontal or profile cascades. I was wondering if there are any specially trained cascades for more accurate face detection within frames that contain faces of variable sizes and with 3/4 turns. If I'm completely off the point here and there is a good way to solve this with cascades available in OpenCV 3.0 please point me in to the right direction.

Thank you