How are threshold images with texture? Tesseract recognition

Question

Original Image:

Target Image:

the code:

cv::Mat sharpenedLena;
cv::Mat kernel = (cv::Mat_<float>(3, 3) << 0, -1, 0, -1, 5, -1, 0, -1, 0);
cv::filter2D(matGrey, sharpenedLena, matGrey.depth(), kernel);
cv::adaptiveThreshold(sharpenedLena, matBinary, 255,    cv::ADAPTIVE_THRESH_GAUSSIAN_C, CV_THRESH_BINARY, 55, 30);
cv::Mat dst_img1;
//cv::GaussianBlur(matBinary, dst_img1, cv::Size(3,3), 0, 0);
cv::medianBlur(matBinary, dst_img1, 3);

UIImage *addrUIImage = [ImageUtil UIImageFromCVMat:dst_img1];
[self recognizeImageWithTesseract:addrUIImage withLauange:1];

Result:

三 胡 南 省 慈利 昙 龙 三 覃 河镇 文

I think it should be a picture related to the problem. Here is the healing effect of others. How to achieve this effect?

Target Image:

Answer 1

Here are my results and code snippet:

Mat mSource_Bgr,mSource_Gray,mSource_Hsv,mThreshold;
mSource_Bgr= imread(FileName_S.c_str(),1);

namedWindow("Source Image",WINDOW_AUTOSIZE);
imshow("Source Image",mSource_Bgr);

cvtColor(mSource_Bgr,mSource_Hsv,COLOR_BGR2HSV);

mSource_Hsv = mSource_Hsv + Scalar(0,0,-25); //Subtracting 25 from all the Pixel Values
cvtColor(mSource_Hsv,mSource_Bgr,COLOR_HSV2BGR);// Back to BGR Just for Debug purpose

imshow("Improved Darkness",mSource_Bgr);
imwrite(FileName_S+"_Res.bmp",mSource_Bgr);

cvtColor(mSource_Bgr,mSource_Gray,COLOR_BGR2GRAY); // for Adaptive Thresholding the input Image

adaptiveThreshold(mSource_Gray,mThreshold,255,ADAPTIVE_THRESH_GAUSSIAN_C,THRESH_BINARY,59,10);

imshow("Adaptive Thres",mThreshold);
imwrite(FileName_S+"_Thres.bmp",mThreshold);

You can remove small Noise dots using the outline region or morphological processing. Hope this helps you!

Answer 2

adaptiveThreshold() , MSER OpenCV.

, MSER, CSER .

Answer 3

You can try using a binary threshold with the OPEN Morphology operation.