Ask Your Question

tidy's profile - activity

2017-06-04 11:12:31 -0500 received badge  Notable Question (source)
2016-04-10 10:36:59 -0500 received badge  Popular Question (source)
2015-03-12 02:53:17 -0500 received badge  Enthusiast
2014-12-24 23:43:30 -0500 asked a question how to remove occlusion from face image?

Any effective method to remove face occlusion? The effect is like the following figure:

image description

Any references for that?

2014-12-08 00:27:40 -0500 commented answer Get the SIFT descriptor for specified point using OpenCV

Thanks for your advice! I will try DSIFT.

2014-12-03 21:19:02 -0500 asked a question Get the SIFT descriptor for specified point using OpenCV

I want get the SIFT feature for specified points. These points is gotten by hand not by KeyPoint Detector. My question is: I only know the position of the points but have no idea about the size and angle value. How should I set this value?

Here is my code:

int main()
{
    SiftDescriptorExtractor extractor;
    Mat descriptors;
    std::vector<KeyPoint> keypoints;

    // set keypoint position and size: should I set size parameter to 32 for 32x32 patch?
    KeyPoint kp(50, 60, 32);
    keypoints.push_back(kp);

    extractor.compute( img_object, keypoints, descriptors );

    return 0;
}

Should I set the size param of KeyPoint to 32 for 32x32 patch. Is this implementation reasonable?

2014-11-18 21:22:59 -0500 asked a question why define MatExpr for opencv mat class?

Any design pattern idea in this class definition?

2014-11-14 00:53:45 -0500 received badge  Editor (source)
2014-11-13 01:32:15 -0500 asked a question how to calculate the detection confidence score for opencv detector

I want to use FDDB to evaluate some face detectors including opencv. But FDDB's detection output file require:

<left_x top_y width height detection_score>

It include a detection_score part. But the opencv's detector have no output like this. How to output this?

2014-10-22 03:49:40 -0500 asked a question opencv split vs mixChannels

To separate hue channel from HSV image, here is the code using the mixChannels function:

/// Transform it to HSV
cvtColor( src, hsv, CV_BGR2HSV );

/// Use only the Hue value
hue.create( hsv.size(), hsv.depth() );
int ch[] = { 0, 0 };
mixChannels( &hsv, 1, &hue, 1, ch, 1 );

But I know split function can also do this:

vector<Mat> chs;
split(hsv, chs);
Mat hue = chs[0];

Is that OK? If these are the same, I think split method is more clean. Am I right?

2014-10-21 21:31:39 -0500 asked a question opencv split vs mixChannels

To separate hue channel from HSV image, here is the code using the mixChannels function:

/// Transform it to HSV
cvtColor( src, hsv, CV_BGR2HSV );

/// Use only the Hue value
hue.create( hsv.size(), hsv.depth() );
int ch[] = { 0, 0 };
mixChannels( &hsv, 1, &hue, 1, ch, 1 );

But I know split function can also do this:

vector<Mat> chs;
split(hsv, chs);
Mat hue = chs[0];

Is that OK? If these are the same, I think split method is more clean. Am I right?

2014-09-19 02:55:20 -0500 asked a question where is createsamples.cpp?

I can not find this file in OpenCV 3.0 alpha now!

2014-09-09 22:13:39 -0500 commented question How do I run opencv_createsamples with multiple positive images?
2014-09-03 21:48:03 -0500 asked a question how to extract gabor feature using opencv?

Does the latest OpenCV version have the function to get this feature?

2014-09-03 21:44:04 -0500 asked a question how to extract gabor feature using opencv?

Does the latest OpenCV version have the function to get this feature?

2014-09-03 21:42:32 -0500 asked a question how to extract gabor feature using opencv?

Does the latest OpenCV version have the function to get this feature?

2014-07-29 21:27:25 -0500 asked a question how to handle occlusion for face recognition?

If there some occlusion on face (such as sunglasses, mask, scarf), the recognition rate will decrease steeply? How to handle this case?

I have do a survey, the PCA reconstruction method have been mentioned by some literature. I don't know whether or not this method is the state-of-the-art method. Is there other method for address occlusion problem?

2014-05-28 01:15:42 -0500 received badge  Scholar (source)
2014-05-26 22:52:38 -0500 asked a question opencv solve linear equation system too slow

I used solve function to solve Ax=b problem. The A is large (about 40000*7000). But it is very slow. Even slower than matlab. By the way, I used the SVD method. Any suggestion?

2014-04-09 01:17:33 -0500 asked a question any face landmark tracking algorithm recommendation?

Is there some tracking alogrithm for face landmark tracking?

2014-03-25 01:51:17 -0500 asked a question How can I use landmark tracking technology to stasm library?

I am using stasm for face landmark detection. It works well for static images. But I want to add tracking algorithm to this library (such as Kalman Filter) to improve the detect effect for video sequence. How can I do this? Any suggestion?

2013-08-07 02:51:52 -0500 received badge  Student (source)
2013-08-05 21:27:05 -0500 asked a question how to use weight when training a weak learner for adaboost

The following is adaboost algorithm:

image description

It mentions "using weights wi on the training data" at part 3.1.

I am not very clear about how to use the weights. Should I resample the training data?