Milanista's profile - activity

Thank you, I´ll try !

Hello! Is it possible to run an OpenCV program on a computer where OpenCV isn't installed? If yes, how? (It gives an error- opencv_core243.dll missing) Thank you!

This is great for fingerprint! Thanks much!

Hello @bsdnoobz. Im using your Zhang-Suen algorith for thinning fingerprints, But I have a problem: I'm looking for minutae int the skeleton with crossing-number method - I check the pixel values in 3x3 blocks. My problem is that with this in some places the width of line is 2 pixels. Whats the problem?

Hi, I tried this function,too, and it works for me (it just makes strange lines from the edges of picture to the fingerprint).

Yes, it can be a constant value, but that's not good for me. In my case it is the angle of fingerprint ridges.

Hi!

I'm asking for a little help with implementing Gabor filter on fingerprint image. I'm computing the kernel in similar function like this. Than I'm applying it to smaller blocks of picture made with ROI and using the orientation in blocks as "theta" parameter and using the kernel with filter2D when visualizing it. So my question is: Can I somehow apply it to the whole picture pixel-by-pixel with theta parameter as orientation of pixel? I hope my question is clear :) Thank you!

Thank you very much!

Hello!

I would like to ask, where exactly the angle computed by carToPolar function points? For example, if I have a 3x3 MAT matrix, and the angle at point [1,1] is 45°, it will point to [2,2] or [0,2] ?

Thank you

I got it, I had the problem somewhere else...

sry for the weird headline :D

Hello!

I'm working on a picture to get the gradients and than compute the angles from it to make a orientation map.

The picture is cropped to 1380x1290 and I'm dividing it into 30x30 blocks.

At first I'm computing the sobel derivates from picture, I store it in CV_16S than I convert it to CV_64F and divide the pixel values by 255 (grad_x.convertTo(abs2_grad_x, CV_64F, 1./255);). Than with carttopolar function I get the angles. I have some problems visualising the whole thing, somehow it draws only 43 columns and 43 rows. I'm doing it this way, what could be wrong?

int xblock= cropped.cols/weight;
int yblock= cropped.rows/weight;

for (int i=0; i < yblock; i++){//rows
for (int j=0; j < xblock; j++){//cols
    for (int m=0; m < weight; m++){//rows
        for (int n=0; n < weight; n++){//cols
            sum = sum + angle.at<double>(i*weight+m,j*weight+n);
        }
    }
    }
}

(In this particular part I'm computing the average of angles in the 30*30 block) Thank you in advance, It's very important for me to continue in my work. (The whole thing looks like it is reflected by the y=x straight)

So I made it this way and it seems to work good, but if I exchange i and j it is the same, I don't understand this...

    for (int i=0; i < xblock; i++){
    for (int j=0; j < yblock; j++){
         for (int m=0; m < weight; m++){
                for (int n=0; n < weight; n++){
                    sum = sum + angle.at<double>(j*weight+m,i*weight+n);
                    magsum = magsum + magnitude.at<double>(j*weight+m,i*weight+n);
                    }
                }

You can choose how do you want the result :) So there will be something wrong in my code/calculatoins :) I hope I can find it.

Are you sure it isnt the same? In documentation I found this: float fastAtan2(float y, float x) - Calculates the angle of a 2D vector in degrees void cartToPolar - Calculates the magnitude and angle of 2d vectors. And if I use your function how could I compute the magnitude of vectors? I got only a point and an angle.

So what should I do now?

7 Computed the destination points of vectors: destination pointx = Sourcepointx + magnitude * cos(angle) destination pointy = Sourcepointy + magnitude * sin(angle) 8 drew lines: cv::line(src, point1, point2, cv::Scalar(0,0,200), 2, CV_AA);
So, am I doing it good?:)

Thank you @StevenPuttemans. I think I'm in the finish line, just something misses. I got this picture, but it doesnt seem very good: http://imageshack.us/photo/my-images/22/orientl.jpg/ I made it this way: 1. I applied Gaussian filter on it : GaussianBlur( src, src, Size(15,15), 0, 0, BORDER_DEFAULT ); 2. I computed gradient for x and y like this : Sobel( src_gray, grad_x, ddepth, 1, 0, 3, scale, delta, BORDER_DEFAULT ); 3. converted it to CV_64F 4. I computed the average of grad in 3030 blocks (I have bigger picture about 12001100) 5. I found this function for getting angle and magnitude : cv::cartToPolar 6. I averaged the angle and magnitude in blocks

Hello @ssvenkatesh6666. How did you get the gradients?

For getting the gradients I used this tutorial: http://docs.opencv.org/doc/tutorials/imgproc/imgtrans/sobel_derivatives/sobel_derivatives.html After it I converted "abs_grad_x" like this: abs_grad_x.convertTo(abs2_grad_x, CV_32F, 1./255); I used "abs2_grad_x" (and y) in your function.

What must be the types of the input gradient containers in your function? If I use CV_8U what is returned from Sobel function it gives me errors. When I converted it to 32F it gives me the same result for each pixel about 44 (degrees if I understand good? )

I asked a question yesterday and I think we are looking for the same thing.. From this question I made the two mat containers of gradients and applied this function on it, but I dont really understand how these thins work :S Should I display the result ? When I try it, i get some errors...

Thank you! I just started to make this part of my program today, I was just stuck a bit with it. I tried some of the things you wrote, so I must be on the correct way. Tomorrow I will continue and I hope I will find the solution. Thanks for the good answer :)

Thank you, I managed to make it :)

Hello. I'm working with fingerprints in openCV c++ and I need to make an orientation map like this:

Could you help me how to do it? I would greet some code,too :)

Hello. Could somebody help me with this: After I load an image I want to separate it into 30x30 pixel blocks then apply wiener filter on it. Now I'm only asking for the separation, how should I do it?