Détection de rayures sur l'image avec beaucoup de bruit

Question

Détection de rayures sur l'image avec beaucoup de bruit

j'ai du mal à détecter scratch sur ces images. En fait, c'est très facile à voir par les yeux humains. Cependant, lors de l'application de certains algorithmes, il y a beaucoup de bruit et je n'ai pas pu extraire l'égratignure seulement.

Voici ces images:

a l'heure actuelle, j'ai essayé certains types de filtre (lissage, moyenne, médiane, filtre gaussien ou détecteur de bord de Sobel) pour effacer le bruit et détecter de rien mais ils ne l'aide pas beaucoup. Pourriez-vous suggérer une idée? Certains outils ou algorithmes que je devrais considérer?

19

computer-vision image-processing opencv

demandé sur SergV 2015-10-20 05:54:55

3 réponses

score 7 · Answer 1

C'est mon implémentation pour la détection de défauts, c'est une approche très simple mais efficace, j'ai implémenté ce code dans MATLAB, mais il n'y a pas de difficulté à le porter sur n'importe quelle langue car il utilise des opérations de traitement d'image de base.

clc

clear all

close all

lire à la fois les Images et les downsample them(pour un calcul rapide) par le facteur de 2.

im1 = imresize(imread('scratch.jpg'),0.5);

les transformer en échelle grise.

gray = rgb2gray(im);

appliquer un filtre gaussien de taille 15 X 15.

gSize = 15;

gray = imfilter(gray,fspecial('gaussian',[gSize,gSize],gSize/2),'replicate');

Trouver Ampleur du Gradient des Images à l'aide de masque de Sobel.

[~,~,mg,~] = ImageFeatures.Gradients(gray);

Gradient de seuil magnitude avec un seuil de 30 percentile de max valeur.

`mgBw = mg > 0,3 * max (mg (:));

appliquer l'opération morpholgical fermeture de l'image binaire par un masque de disque de 3 X 3.

mgBw = imclose(mgBw,strel('disk',1));

Appliquer Particules Analyser (CCL).

mgBw = bwareaopen(mgBw,500);

encore une fois fermez L'Image pour joindre les lignes ensemble.

mgBw = imclose(mgBw,strel('disk',2));

remplir les trous dans le image.

mgBw = imfill(mgBw,'holes');

Annotations Finales:

Essayez la procédure ci-Dessus sur vos images espère que cela va fonctionner

Merci

les valeurs pour le masque gaussien sont données ci-dessous je viens de copier comme il est, vous pouvez seulement utilisez les valeurs 4 places après la décimale et encore une chose avant l'échelle de convolution vos valeurs d'image entre 0 et 1:

         0.00253790859361804,0.00284879446220838,0.00314141610419987,0.00340305543986557,0.00362152753952273,0.00378611472031542,0.00388843599983945,0.00392315394879368,0.00388843599983945,0.00378611472031542,0.00362152753952273,0.00340305543986557,0.00314141610419987,0.00284879446220838,0.00253790859361804;
         0.00284879446220838,0.00319776287779517,0.00352622975612324,0.00381991909245893,0.00406515334132644,0.00424990193722614,0.00436475725361032,0.00440372804277458,0.00436475725361032,0.00424990193722614,0.00406515334132644,0.00381991909245893,0.00352622975612324,0.00319776287779517,0.00284879446220838;
         0.00314141610419987,0.00352622975612324,0.00388843599983945,0.00421229243210782,0.00448271658130972,0.00468644212981339,0.00481309512122034,0.00485606890058492,0.00481309512122034,0.00468644212981339,0.00448271658130972,0.00421229243210782,0.00388843599983945,0.00352622975612324,0.00314141610419987;
         0.00340305543986557,0.00381991909245893,0.00421229243210782,0.00456312191696750,0.00485606890058492,0.00507676215263394,0.00521396370030743,0.00526051663974220,0.00521396370030743,0.00507676215263394,0.00485606890058492,0.00456312191696750,0.00421229243210782,0.00381991909245893,0.00340305543986557;
         0.00362152753952273,0.00406515334132644,0.00448271658130972,0.00485606890058492,0.00516782273108746,0.00540268422664802,0.00554869395001131,0.00559823553262373,0.00554869395001131,0.00540268422664802,0.00516782273108746,0.00485606890058492,0.00448271658130972,0.00406515334132644,0.00362152753952273;
         0.00378611472031542,0.00424990193722614,0.00468644212981339,0.00507676215263394,0.00540268422664802,0.00564821944786971,0.00580086485975791,0.00585265795345929,0.00580086485975791,0.00564821944786971,0.00540268422664802,0.00507676215263394,0.00468644212981339,0.00424990193722614,0.00378611472031542;
         0.00388843599983945,0.00436475725361032,0.00481309512122034,0.00521396370030743,0.00554869395001131,0.00580086485975791,0.00595763557555571,0.00601082839853353,0.00595763557555571,0.00580086485975791,0.00554869395001131,0.00521396370030743,0.00481309512122034,0.00436475725361032,0.00388843599983945;
         0.00392315394879368,0.00440372804277458,0.00485606890058492,0.00526051663974220,0.00559823553262373,0.00585265795345929,0.00601082839853353,0.00606449615428972,0.00601082839853353,0.00585265795345929,0.00559823553262373,0.00526051663974220,0.00485606890058492,0.00440372804277458,0.00392315394879368;
         0.00388843599983945,0.00436475725361032,0.00481309512122034,0.00521396370030743,0.00554869395001131,0.00580086485975791,0.00595763557555571,0.00601082839853353,0.00595763557555571,0.00580086485975791,0.00554869395001131,0.00521396370030743,0.00481309512122034,0.00436475725361032,0.00388843599983945;
         0.00378611472031542,0.00424990193722614,0.00468644212981339,0.00507676215263394,0.00540268422664802,0.00564821944786971,0.00580086485975791,0.00585265795345929,0.00580086485975791,0.00564821944786971,0.00540268422664802,0.00507676215263394,0.00468644212981339,0.00424990193722614,0.00378611472031542;
         0.00362152753952273,0.00406515334132644,0.00448271658130972,0.00485606890058492,0.00516782273108746,0.00540268422664802,0.00554869395001131,0.00559823553262373,0.00554869395001131,0.00540268422664802,0.00516782273108746,0.00485606890058492,0.00448271658130972,0.00406515334132644,0.00362152753952273;
         0.00340305543986557,0.00381991909245893,0.00421229243210782,0.00456312191696750,0.00485606890058492,0.00507676215263394,0.00521396370030743,0.00526051663974220,0.00521396370030743,0.00507676215263394,0.00485606890058492,0.00456312191696750,0.00421229243210782,0.00381991909245893,0.00340305543986557;
         0.00314141610419987,0.00352622975612324,0.00388843599983945,0.00421229243210782,0.00448271658130972,0.00468644212981339,0.00481309512122034,0.00485606890058492,0.00481309512122034,0.00468644212981339,0.00448271658130972,0.00421229243210782,0.00388843599983945,0.00352622975612324,0.00314141610419987;
         0.00284879446220838,0.00319776287779517,0.00352622975612324,0.00381991909245893,0.00406515334132644,0.00424990193722614,0.00436475725361032,0.00440372804277458,0.00436475725361032,0.00424990193722614,0.00406515334132644,0.00381991909245893,0.00352622975612324,0.00319776287779517,0.00284879446220838;
         0.00253790859361804,0.00284879446220838,0.00314141610419987,0.00340305543986557,0.00362152753952273,0.00378611472031542,0.00388843599983945,0.00392315394879368,0.00388843599983945,0.00378611472031542,0.00362152753952273,0.00340305543986557,0.00314141610419987,0.00284879446220838,0.00253790859361804;

Masque De Sobel:

 1, 2, 1;
 0, 0, 0;
-1,-2, 1;

et

 1, 0,-1;
 2, 0,-2;
 1, 0,-1;

Code De Magnitude Du Gradient De Sobel (ImageFeatures.Dégradé):

function [gx,gy,mag,phi] = Gradients(gray)
    gray = double(gray);
    horzmask = fspecial('sobel');
  %  vertmask = horzmask';

    gx = imfilter(gray,horzmask,'replicate');
    gy = imfilter(gray,horzmask','replicate');

    phi = (atan2((gy),(gx)));

    mag = mat2gray(sqrt(gx.^2+gy.^2));
end

score 2 · Answer 2

j'ai essayé la procédure suivante pour la détection. La production semble modérée, mais j'ai quand même pensé à partager.

sous-échantillonner l'image couleur.
appliquer le flou médian avec différentes tailles de fenêtre, puis prendre la différence absolue: je le fais pour améliorer les marques de rayure et en même temps obtenir l'éclairage aplatissement. Ci-dessous sont les différentes images obtenues façon.
utilisez une segmentation de fond/premier plan basée sur un mélange gaussien pour segmenter les marques de rayure dans l'image de différence. Idée ici est, nous pouvons extraire m x N fenêtres de cette image et de former. Comme les rayures n'occupent pas une grande surface dans l'image de différence, nous pouvons penser que le fond appris devrait se rapprocher de la région à l'extérieur des rayures. Cette méthode fonctionnait mieux pour les deux la différence des images que l'application d'un seuil à l'image de différence. Cette méthode n'a pas bien fonctionné quand j'ai alimenté l'image downsampled directement. Je pense que cela est dû à la nature non uniforme des valeurs de couleur des pixels dans les régions. J'ai donc utilisé l'image de différence aplatie de l'éclairage. Voici les images segmentées. Cette procédure est lente car elle vérifie toutes les fenêtres m x n image.
utiliser la Transformée de Hough probabiliste pour détecter les lignes dans l'image segmentée. En utilisant la densité des lignes dans les régions ou en utilisant le filtrage morphologique pour les lignes, je pense qu'il est possible d'arriver à une estimation raisonnable quant à l'endroit où les marques de rayure sont.

Voici le code

arrière-plan de la segmentation code:

Mat threshold_mog(Mat& im, Size window)
{
    BackgroundSubtractorMOG2 bgModel;
    Mat fgMask;
    Mat output = Mat::ones(im.rows, im.cols, CV_8U);

    for (int r = 0; r < im.rows - window.height; r++)
    {
        for (int c = 0; c < im.cols - window.width; c++)
        {
            bgModel.operator()(im(Rect(c, r, window.width, window.height)), fgMask);
        }
    }

    for (int r = 0; r < im.rows - window.height; r++)
    {
        for (int c = 0; c < im.cols - window.width; c++)
        {
            Mat region = im(Rect(c, r, window.width, window.height));
        bgModel.operator()(region, fgMask, 0);
            fgMask.copyTo(output(Rect(c, r, window.width, window.height)));
        }
    }

    return output;
}

main:

Mat rgb = imread("scratch_2.png.jpg");

pyrDown(rgb, rgb);

Mat med, med2, dif, bw;

medianBlur(rgb, med, 3);
medianBlur(rgb, med2, 21);

absdiff(med2, med, dif);

bw = threshold_mog(dif, Size(15, 15));

Mat dst = bw.clone();
vector<Vec4i> lines;
HoughLinesP(dst, lines, 1, CV_PI/180, 8, 10, 20);
for( size_t i = 0; i < lines.size(); i++ )
{
    Vec4i l = lines[i];
    line(rgb, Point(l[0], l[1]), Point(l[2], l[3]), Scalar(0,0,255), 1, CV_AA);
}

score 0 · Answer 3

je suis la procédure D'Ankit Dixit pour détecter les égratignures et avoir des problèmes. Tout d'abord, parce que j'utilise C++ au lieu de MATLAB, donc je voudrais vérifier s'il y a malentendu sur l'algorithme.

pour l'instant, je n'utilise que le filtre gaussien 5x5 car il est disponible. Quelle est la raison pour laquelle vous avez choisi la taille de la fenêtre 15x15 au lieu de 5x5? Deuxièmement, mon image après le masque de Sobel ne semble pas aussi bonne que la vôtre. Est-ce qu'il y a une différence avec Sobel? Matlab?

Voici des images: Gris: http://s15.postimg.org/q8s5y2sjf/Gray_Image.png Filtre gaussien 5x5: http://s1.postimg.org/80r9x20tr/Gaussian_Filter_5x5.png Faire Sobel: http://s21.postimg.org/vxwyju58n/Sobel_Image.png

Las etiquetas más populares

Détection de rayures sur l'image avec beaucoup de bruit

3 réponses