我正在尝试清理上面的图像我尝试了几种使用open cv的不同方法,我要么过多地侵蚀原始图像,使得部分字母丢失,如下所示:
我不确定如何摆脱最后一条对角线并修复S,到目前为止我的代码是:
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')
还指向包含images
的文件夹的链接答案 0 :(得分:20)
这是一个使用OpenCvSharp的C#解决方案(应该很容易转换回python / c ++,因为方法名称完全相同)。
它使用OpenCV的inpainting技术来避免在可能运行OCR阶段之前销毁过多的字母。我们可以看到线条的颜色与其他颜色不同,所以我们会在任何灰度/黑白之前很早就使用这些信息。步骤如下:
这是面具:
结果如下:
以下是样本集的结果:
这是C#代码:
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)));
}
}
}
}
}
}
答案 1 :(得分:7)
仔细查看验证码。该图像中的大部分灰尘与文本具有不同的灰度值。
文字在140
,灰尘在112
。
简单的灰度过滤在这里会有很多帮助。
from scipy.misc import imread, imsave
import numpy as np
infile = "A1nO4.png"
outfile = "A1nO4_out.png"
im = imread(infile, True)
out_im = np.ones(im.shape) * 255
out_im[im == 140] = 0
imsave(outfile, out_im)
现在使用cv2.dilate
(cv2.erode
在黑色文本上的白色)来消除剩余的灰尘。