检测具有大量噪声的图像上的划痕
Posted
技术标签:
【中文标题】检测具有大量噪声的图像上的划痕【英文标题】：Detecting scratch on image with much noise 【发布时间】：2015-10-20 02:54:55 【问题描述】：我在检测这些图像上的划痕时遇到了问题。实际上，人眼很容易看到。但是，在应用某些算法时，噪音很大，我无法仅提取划痕。
以下是这些图片：
目前，我尝试了一些过滤器（平滑、平均、中值、高斯过滤器或 Sobel 边缘检测器）来消除噪声和检测划痕，但它们并没有太大帮助。 你能提出一些想法吗？ 我应该考虑一些工具或算法？
【问题讨论】：
我只是看了你的图片，我不知道什么是划痕，什么是正常特征。三个平行的大斜线是划痕，还是左边斜线的小横线？ 嗨，划痕是三个平行的大斜线。 使用重复帖子中的想法。重复的帖子走得更远，并删除了图像中的划痕。只需使用票数最高的答案的前半部分。 这绝对不是所列问题的重复。这个问题是关于自动检测划痕，另一个问题是关于去除划痕（当你知道它在哪里时）。我建议重新打开。 @DanivanderMeer 我的错。你是对的。我应该更好地阅读这篇文章。重新开放。 【参考方案1】：这是我对缺陷检测的实现，它是一种非常简单而有效的方法，我已经在 MATLAB 中实现了此代码，但由于它使用基本的图像处理操作，因此将其移植到任何语言上都没有任何困难。
clc
clear all
close all
-
读取两个图像并将它们下采样（用于快速计算）2 倍。
im1 = imresize(imread('scratch.jpg'),0.5);
-
将它们转换为灰度。
gray = rgb2gray(im);
-
应用大小为 15 X 15 的高斯滤波器。
gSize = 15;
gray = imfilter(gray,fspecial('gaussian',[gSize,gSize],gSize/2),'replicate');
-
使用 Sobel 蒙版找出图像的梯度幅度。
[~,~,mg,~] = ImageFeatures.Gradients(gray);
-
阈值梯度幅度，阈值为最大值的 30%。
`mgBw = mg > 0.3*max(mg(:));
-
应用形态运算通过 3 X 3 的磁盘掩码关闭二进制图像。
mgBw = imclose(mgBw,strel('disk',1));
-
应用粒子分析 (CCL)。
mgBw = bwareaopen(mgBw,500);
-
再次关闭图像以将线条连接在一起。
mgBw = imclose(mgBw,strel('disk',2));
-
填充图像中的孔。
mgBw = imfill(mgBw,'holes');
-
最终注释：
在您的图像上尝试上述过程，希望它会起作用
谢谢
下面给出了高斯蒙版的值，我只是按原样复制的，您只能使用小数点后 4 位的值，以及在卷积之前将图像值缩放到 0 和 1 之间的另一件事：
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;
索贝尔面具：
1, 2, 1;
0, 0, 0;
-1,-2, 1;
和
1, 0,-1;
2, 0,-2;
1, 0,-1;
Sobel 梯度幅度代码(ImageFeatures.Gradient)：
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
【讨论】：
嗯，非常令人印象深刻！我将在 C++ 中尝试此过程，并在完成后发布结果。 参数太多.. 我很肯定它不适用于稍微不同的条件 试试吧老兄...在示例中只有两个图像...算法总是根据数据可用性设计的。 这种技术的来源是什么？我的意思是，你是如何/在哪里找到它的？任何文章/书籍/引文/任何东西？ 经验是技术的来源:)【参考方案2】：我尝试了以下检测程序。输出看起来适中，但我还是想到了分享。
对彩色图像进行下采样。应用不同窗口大小的中值模糊，然后取绝对差异：我这样做是为了增强划痕，同时实现照明平坦化。下面显示的是通过这种方式获得的差异图像。
使用基于高斯混合的背景/前景分割来分割差异图像中的划痕。这里的想法是，我们可以从该图像中提取 m x n 个窗口并进行训练。由于划痕在差异图像中所占区域不大，我们可以认为学习到的背景应该近似于划痕之外的区域。这种方法对两个差异图像都比对差异图像应用阈值效果更好。当我直接输入下采样图像时，此方法效果不佳。我认为这是由于区域中像素颜色值的不均匀性。所以我使用了照明扁平化的差异图像。下面是分段的图像。这个过程很慢，因为它检查图像中每个可能的 m x n 窗口。
使用概率霍夫变换来检测分割图像中的线条。使用区域中的线密度或使用线的形态过滤，我认为可以对划痕的位置进行合理的猜测。
这是代码
背景分割代码：
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;
主要：
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);
【讨论】：
谢谢大家。似乎已经足够好了。我现在正在写霍夫变换。 @anhnha 你能用 C++ 完成它吗？能发下源代码供参考吗？ @user1220497 已经很久了，现在我在另一个领域工作以上是关于检测具有大量噪声的图像上的划痕的主要内容，如果未能解决你的问题，请参考以下文章