OpenCV自适应阈值OCR
我正在使用OpenCV从iPhone相机准备OCR图像,我一直无法获得准确的OCR扫描所需的结果.这是我现在使用的代码.
cv::cvtColor(cvImage, cvImage, CV_BGR2GRAY);
cv::medianBlur(cvImage, cvImage, 0);
cv::adaptiveThreshold(cvImage, cvImage, 255, CV_ADAPTIVE_THRESH_MEAN_C, CV_THRESH_BINARY, 5, 4);
这种方法需要花费太长时间,并没有给我带来好的结果.
关于如何使这更有效的任何建议？这些图像来自iPhone相机.
在使用安德里的建议之后.
cv::Mat cvImage = [self cvMatFromUIImage:image];
cv::Mat res;
cv::cvtColor(cvImage, cvImage, CV_RGB2GRAY);
cvImage.convertTo(cvImage,CV_32FC1,1.0/255.0);
CalcBlockMeanVariance(cvImage,res);
res=1.0-res;
res=cvImage+res;
cv::threshold(res,res, 0.85, 1, cv::THRESH_BINARY);
cv::resize(res, res, cv::Size(res.cols/2,res.rows/2));
image = [self UIImageFromCVMat:cvImage];
方法:
void CalcBlockMeanVariance(cv::Mat Img,cv::Mat Res,float blockSide=21) // blockSide - the parameter (set greater for larger font on image)
{
cv::Mat I;
Img.convertTo(I,CV_32FC1);
Res=cv::Mat::zeros(Img.rows/blockSide,Img.cols/blockSide,CV_32FC1);
cv::Mat inpaintmask;
cv::Mat patch;
cv::Mat smallImg;
cv::Scalar m,s;
for(int i=0;i<Img.rows-blockSide;i+=blockSide)
{
for (int j=0;j<Img.cols-blockSide;j+=blockSide)
{
patch=I(cv::Rect(j,i,blockSide,blockSide));
cv::meanStdDev(patch,m,s);
if(s[0]>0.01) // Thresholding parameter (set smaller for lower contrast image)
{
Res.at<float>(i/blockSide,j/blockSide)=m[0];
}else
{
Res.at<float>(i/blockSide,j/blockSide)=0;
}
}
}
cv::resize(I,smallImg,Res.size());
cv::threshold(Res,inpaintmask,0.02,1.0,cv::THRESH_BINARY);
cv::Mat inpainted;
smallImg.convertTo(smallImg,CV_8UC1,255);
inpaintmask.convertTo(inpaintmask,CV_8UC1);
inpaint(smallImg, inpaintmask, inpainted, 5, cv::INPAINT_TELEA);
cv::resize(inpainted,Res,Img.size());
Res.convertTo(Res,CV_32FC1,1.0/255.0);
}
知道为什么我得到这个结果吗？OCR的结果相当不错,但如果我能得到一张类似你得到的图像会更好.如果重要的话,我正在为iOS开发.我不得不使用,cvtColor因为该方法需要单个通道图像.
And*_*dov 19
这是我的结果:
这是代码:
#include <iostream>
#include <vector>
#include <stdio.h>
#include <stdarg.h>
#include "opencv2/opencv.hpp"
#include "fstream"
#include "iostream"
using namespace std;
using namespace cv;
//-----------------------------------------------------------------------------------------------------
//
//-----------------------------------------------------------------------------------------------------
void CalcBlockMeanVariance(Mat& Img,Mat& Res,float blockSide=21) // blockSide - the parameter (set greater for larger font on image)
{
Mat I;
Img.convertTo(I,CV_32FC1);
Res=Mat::zeros(Img.rows/blockSide,Img.cols/blockSide,CV_32FC1);
Mat inpaintmask;
Mat patch;
Mat smallImg;
Scalar m,s;
for(int i=0;i<Img.rows-blockSide;i+=blockSide)
{
for (int j=0;j<Img.cols-blockSide;j+=blockSide)
{
patch=I(Range(i,i+blockSide+1),Range(j,j+blockSide+1));
cv::meanStdDev(patch,m,s);
if(s[0]>0.01) // Thresholding parameter (set smaller for lower contrast image)
{
Res.at<float>(i/blockSide,j/blockSide)=m[0];
}else
{
Res.at<float>(i/blockSide,j/blockSide)=0;
}
}
}
cv::resize(I,smallImg,Res.size());
cv::threshold(Res,inpaintmask,0.02,1.0,cv::THRESH_BINARY);
Mat inpainted;
smallImg.convertTo(smallImg,CV_8UC1,255);
inpaintmask.convertTo(inpaintmask,CV_8UC1);
inpaint(smallImg, inpaintmask, inpainted, 5, INPAINT_TELEA);
cv::resize(inpainted,Res,Img.size());
Res.convertTo(Res,CV_32FC1,1.0/255.0);
}
//-----------------------------------------------------------------------------------------------------
//
//-----------------------------------------------------------------------------------------------------
int main( int argc, char** argv )
{
namedWindow("Img");
namedWindow("Edges");
//Mat Img=imread("D:\\ImagesForTest\\BookPage.JPG",0);
Mat Img=imread("Test2.JPG",0);
Mat res;
Img.convertTo(Img,CV_32FC1,1.0/255.0);
CalcBlockMeanVariance(Img,res);
res=1.0-res;
res=Img+res;
imshow("Img",Img);
cv::threshold(res,res,0.85,1,cv::THRESH_BINARY);
cv::resize(res,res,cv::Size(res.cols/2,res.rows/2));
imwrite("result.jpg",res*255);
imshow("Edges",res);
waitKey(0);
return 0;
}
- 也许你应该为你的方法和代码添加更多的解释. (10认同)
- 是的，图像必须转换为灰度。我没有这样做，因为 Mat Img=imread("Test2.JPG",0); 以灰度加载图像。 (2认同)
- 我不是iOS编程的专家,但你的输出图像是彩色图像,所以我认为你错过了颜色到灰色的转换.在运行时使用调试器检查图像类型.输出格式图像也可能存在问题.可能是您需要在显示之前将结果转换回BGR. (2认同)
JAVA CODE:自问题提出以来已经过了很长时间,但是我已经将这个代码从C++重写为Java,以防有人需要它(我需要用它在android studio上开发应用程序).
public Bitmap Thresholding(Bitmap bitmap)
{
Mat imgMat = new Mat();
Utils.bitmapToMat(bitmap, imgMat);
imgMat.convertTo(imgMat, CvType.CV_32FC1, 1.0 / 255.0);
Mat res = CalcBlockMeanVariance(imgMat, 21);
Core.subtract(new MatOfDouble(1.0), res, res);
Imgproc.cvtColor( imgMat, imgMat, Imgproc.COLOR_BGRA2BGR);
Core.add(imgMat, res, res);
Imgproc.threshold(res, res, 0.85, 1, Imgproc.THRESH_BINARY);
res.convertTo(res, CvType.CV_8UC1, 255.0);
Utils.matToBitmap(res, bitmap);
return bitmap;
}
public Mat CalcBlockMeanVariance (Mat Img, int blockSide)
{
Mat I = new Mat();
Mat ResMat;
Mat inpaintmask = new Mat();
Mat patch;
Mat smallImg = new Mat();
MatOfDouble mean = new MatOfDouble();
MatOfDouble stddev = new MatOfDouble();
Img.convertTo(I, CvType.CV_32FC1);
ResMat = Mat.zeros(Img.rows() / blockSide, Img.cols() / blockSide, CvType.CV_32FC1);
for (int i = 0; i < Img.rows() - blockSide; i += blockSide)
{
for (int j = 0; j < Img.cols() - blockSide; j += blockSide)
{
patch = new Mat(I,new Rect(j,i, blockSide, blockSide));
Core.meanStdDev(patch, mean, stddev);
if (stddev.get(0,0)[0] > 0.01)
ResMat.put(i / blockSide, j / blockSide, mean.get(0,0)[0]);
else
ResMat.put(i / blockSide, j / blockSide, 0);
}
}
Imgproc.resize(I, smallImg, ResMat.size());
Imgproc.threshold(ResMat, inpaintmask, 0.02, 1.0, Imgproc.THRESH_BINARY);
Mat inpainted = new Mat();
Imgproc.cvtColor(smallImg, smallImg, Imgproc.COLOR_RGBA2BGR);
smallImg.convertTo(smallImg, CvType.CV_8UC1, 255.0);
inpaintmask.convertTo(inpaintmask, CvType.CV_8UC1);
Photo.inpaint(smallImg, inpaintmask, inpainted, 5, Photo.INPAINT_TELEA);
Imgproc.resize(inpainted, ResMat, Img.size());
ResMat.convertTo(ResMat, CvType.CV_32FC1, 1.0 / 255.0);
return ResMat;
}