清理验证码图像

本文介绍了清理验证码图像的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！ 问题描述

我正在尝试清理上面的图片我尝试了几种使用open cv的不同方法，我要么将原始图像过度侵蚀到部分字母丢失的程度，如下所示：

还指向包含 <这是结果：

以下是样本集的结果：

这是C＃代码：

static void Decaptcha（string filePath） { //使用（var src = new Mat（filePath））加载文件 { using（var binaryMask = new Mat（）） { //行颜色不同于文本 var linesColor = Scalar.FromRgb（0x70,0x70,0x70）; //构建一个行掩码 Cv2.InRange（src，linesColor，linesColor，binaryMask）; using（var masked = new Mat（）） { //构建相应的图像 //稍微扩张一行，因为在屏蔽期间别名可能过多地过滤了边框 src.CopyTo（masked，binaryMask）; int linesDilate = 3; using（var element = Cv2.GetStructuringElement（MorphShapes.Ellipse，new Size（linesDilate，linesDilate））） { Cv2.Dilate（masked，masked，element）; } //将蒙版转换为灰度 Cv2.CvtColor（蒙版，蒙面，ColorConversionCodes.BGR2GRAY）; using（var dst = src.EmptyClone（）） { //重绘大行 Cv2.Inpaint（src，masked，dst，3，InpaintMethod.NS）; //销毁小行 linesDilate = 2; using（var element = Cv2.GetStructuringElement（MorphShapes.Ellipse，new Size（linesDilate，linesDilate））） { Cv2.Dilate（dst，dst，element）; } Cv2.GaussianBlur（dst，dst，new Size（5,5），0）; 使用（var dst2 = dst.BilateralFilter（5,75,75）） { //基本上使它成为B& W Cv2.CvtColor（dst2，dst2，ColorConversionCodes） .BGR2GRAY）; Cv2.Threshold（dst2，dst2,255,255，ThresholdTypes.Otsu）; //保存文件 dst2.SaveImage（Path.Combine（ Path.GetDirectoryName（filePath）， Path.GetFileNameWithoutExtension（filePath）+_ dst + Path.GetExtension（filePath）））; } } } } } }

I'm trying to clean up the image above I've tried several different methods using open cv, I either erode the original image too much to the point where parts of the letters become missing such as below:

I'm not really sure sure how to get rid of the last diagonal line and repair the S, my code so far is:

import cv2 import matplotlib.pylab as plt img = cv2.imread('/captcha_3blHDdS.png') #make image gray gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY) #Blur blur = cv2.GaussianBlur(gray,(5,5),0) bilateral = cv2.bilateralFilter(gray,5,75,75) #Thresholding ret, thresh = cv2.threshold(bilateral,25,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU) #Kernal kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3)) #other things erosion = cv2.erode(thresh,kernel,iterations = 1) closing = cv2.morphologyEx(erosion, cv2.MORPH_CLOSE, kernel, iterations = 1) #Transform image dist_transform = cv2.distanceTransform(closing,cv2.DIST_L2,5) ret, sure_fg = cv2.threshold(dist_transform,0.02*dist_transform.max(),255,cv2.THRESH_BINARY)#,255,0) #kernel_1 kernel_1 = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (1, 2)) dilation_1 = cv2.dilate(sure_fg,kernel_1,iterations = 2) erosion_1 = cv2.erode(dilation_1,kernel_1,iterations = 3) plt.imshow(erosion_1, 'gray')

Any help would be greatly appreciated, Here are more examples of the type of images that are produced from the captcha;

also heres the link to a folder containing the images

解决方案

Here is a C# solution using OpenCvSharp (which should be easy to convert back to python/c++ because the method names are exactly the same).

It uses OpenCV's inpainting technique to avoid destroying too much of the letters before possibly running an OCR phase. We can see that the lines have a different color than the rest, so we'll use that information very early, before any grayscaling/blackwhiting. Steps are as follow:

• build a mask from the lines using their color (#707070)
• dilate that mask a bit because the lines may have been drawn with antialiasing
• repaint ("inpaint") the original image using this mask, which will remove the lines while preserving most of what was below the lines (letters). Note we could remove the small points before that step, I think it would be even better
• apply some dilate/blur/threshold to finalize

Here is the mask:

Here is the result:

Here is the result on sample set:

Here is the C# code:

static void Decaptcha(string filePath) { // load the file using (var src = new Mat(filePath)) { using (var binaryMask = new Mat()) { // lines color is different than text var linesColor = Scalar.FromRgb(0x70, 0x70, 0x70); // build a mask of lines Cv2.InRange(src, linesColor, linesColor, binaryMask); using (var masked = new Mat()) { // build the corresponding image // dilate lines a bit because aliasing may have filtered borders too much during masking src.CopyTo(masked, binaryMask); int linesDilate = 3; using (var element = Cv2.GetStructuringElement(MorphShapes.Ellipse, new Size(linesDilate, linesDilate))) { Cv2.Dilate(masked, masked, element); } // convert mask to grayscale Cv2.CvtColor(masked, masked, ColorConversionCodes.BGR2GRAY); using (var dst = src.EmptyClone()) { // repaint big lines Cv2.Inpaint(src, masked, dst, 3, InpaintMethod.NS); // destroy small lines linesDilate = 2; using (var element = Cv2.GetStructuringElement(MorphShapes.Ellipse, new Size(linesDilate, linesDilate))) { Cv2.Dilate(dst, dst, element); } Cv2.GaussianBlur(dst, dst, new Size(5, 5), 0); using (var dst2 = dst.BilateralFilter(5, 75, 75)) { // basically make it B&W Cv2.CvtColor(dst2, dst2, ColorConversionCodes.BGR2GRAY); Cv2.Threshold(dst2, dst2, 255, 255, ThresholdTypes.Otsu); // save the file dst2.SaveImage(Path.Combine( Path.GetDirectoryName(filePath), Path.GetFileNameWithoutExtension(filePath) + "_dst" + Path.GetExtension(filePath))); } } } } } }