CODEWITHSUNDEEP
opencvfingerprint
jcgarciaca
jcgarciaca

Reputation: 139

Region of interest in fingerprint image

I am working on a fingerprint recognition project with OpenCV. Currently I need to extract the inner region in fingerprint (ellipse in image), but I am not sure how to do it.

enter image description here

Any suggestion is appreciated.

EDIT:

I need to check if a fingerprint from sensor device and another from identification card match or not. The fingerprint in sensor is as follow (left) meanwhile in identification card is as right fingerprint. In order to validate them, it is required to segment this fingerprint (outside the ellipse doesn't provide useful information but indeed adds "noise" for this purpose).

enter image description here

Thank you.

Upvotes: 1

Views: 904

Answers (2)

Ali Abbas
Ali Abbas

Reputation: 1

int main() {

    string path = "Resources/1/*";

    vector<String> fn;
    vector<Mat> data;
    glob(path, fn, true);
    int cntr = 0;
    Mat inputImage, binaryimage;

    for (size_t k = 0; k < fn.size(); ++k){

        inputImage = imread(fn[k]);
        cout << fn[k] << endl;

        Mat gray;
        cvtColor(inputImage,gray, COLOR_BGR2GRAY);

        Mat normalizedImage;
        cv::normalize(gray, normalizedImage, 15, 255, NORM_MINMAX);
        imshow("inpnorm", normalizedImage);

        Mat imgdil, imgerode;
        Mat kernel = getStructuringElement(MORPH_ELLIPSE, Size(3, 3));
        dilate(normalizedImage, imgdil, kernel);
        //erode(imgdil, imgerode, kernel);

        Mat normalizImg;
        cv::normalize(imgdil, normalizImg, 25, 255, NORM_MINMAX);
        cv::normalize(normalizImg, normalizImg, 25, 255, NORM_MINMAX);

        Mat thre;
        adaptiveThreshold(normalizImg, thre, 255, ADAPTIVE_THRESH_MEAN_C, THRESH_BINARY_INV, 25, 1.9);

        cv::normalize(thre, normalizImg, 15, 255, NORM_MINMAX);
        cv::normalize(normalizImg, normalizImg, 15, 255, NORM_MINMAX);
        cv::normalize(normalizImg, thre, 17, 255, NORM_MINMAX); 

        string savingName = "fingerprints00/" + to_string(++cntr) + ".jpg";
        imwrite(savingName, thre);

        imshow("original image", inputImage);
        //imshow("norm", normalizImg);
        imshow("thresh", thre);
        moveWindow("original image",0,0);
        moveWindow("thresh",600,0);
        waitKey(0);
    }

    return 0;
}

opencv c++ for fingerprint extraction from finger image,change the path, thank me later

Upvotes: 0

GPPK
GPPK

Reputation: 6666

@API55's comment is correct, for clarity:

create a mask (white inside the ellipse and black outside) you can do this with ellipse function and -1 in the thickness. Then copy the image using the mask (bitwise_and for python or copyTo for c++ should do it)... you will always have a squared image, but you will have black (or the color you want) outside the ellipse

These steps are pretty much spot on,

  1. Create your circular mask in the correct place in the image
  2. Copy the image using that mask
  3. Your new image contains the mask data, and black data everywhere else.

below is an example of how to implement this in code:

( I lovingly borrowed from here)

Mat img = imread("small1.png", 0); // load gray
Rect region(10,10,40,40); // example roi
Mat roi(img, region);  // part of img
Mat mask(Size(40,40), CV_8U, Scalar(0)); // all black
circle(mask, Point(20,20), 20, Scalar(255), -1, LINE_AA); // filled circle
Mat circRoi;
bitwise_and(roi, roi, circRoi, mask); // retain only pixels inside the circle
//
// now you can do your intensity calculation on circRoi
//
imshow("circle masked", mask);
imshow("masked roi", circRoi);
waitKey();

Useful Links

Upvotes: 1

Related Questions