tidy's profile - activity

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

Any references for that?

Thanks for your advice! I will try DSIFT.

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?

Any design pattern idea in this class definition?

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?

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?

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?

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

try this: https://github.com/wulfebw/mergevec

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

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

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

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?

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?

Is there some tracking alogrithm for face landmark tracking?

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?

The following is adaboost algorithm:

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?