I am using OpenCV to prepare images for OCR from an iPhone camera, and I have been having trouble getting the results I need for an accurate OCR scan. Here is the code I am using now.
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);
This method takes a bit too long and does not provide me good results.
Any suggestions on how I could make this more effective? The images are coming from an iPhone camera.
After using Andry's suggestion.
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];
Method:
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);
}
Any idea why I am getting this result? The OCR results are pretty good, but would be better if I could get an image similar to the one you got. I am developing for iOS if that matters. I had to use cvtColor
because the method expects a single channel image.
Here is my result:
Here is the code:
#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;
}
And Python port:
import cv2 as cv
import numpy as np
#-----------------------------------------------------------------------------------------------------
#
#-----------------------------------------------------------------------------------------------------
def CalcBlockMeanVariance(Img,blockSide=21): # blockSide - the parameter (set greater for larger font on image)
I=np.float32(Img)/255.0
Res=np.zeros( shape=(int(Img.shape[0]/blockSide),int(Img.shape[1]/blockSide)),dtype=np.float)
for i in range(0,Img.shape[0]-blockSide,blockSide):
for j in range(0,Img.shape[1]-blockSide,blockSide):
patch=I[i:i+blockSide+1,j:j+blockSide+1]
m,s=cv.meanStdDev(patch)
if(s[0]>0.001): # Thresholding parameter (set smaller for lower contrast image)
Res[int(i/blockSide),int(j/blockSide)]=m[0]
else:
Res[int(i/blockSide),int(j/blockSide)]=0
smallImg=cv.resize(I,(Res.shape[1],Res.shape[0] ) )
_,inpaintmask=cv.threshold(Res,0.02,1.0,cv.THRESH_BINARY);
smallImg=np.uint8(smallImg*255)
inpaintmask=np.uint8(inpaintmask)
inpainted=cv.inpaint(smallImg, inpaintmask, 5, cv.INPAINT_TELEA)
Res=cv.resize(inpainted,(Img.shape[1],Img.shape[0] ) )
Res=np.float32(Res)/255
return Res
#-----------------------------------------------------------------------------------------------------
#
#-----------------------------------------------------------------------------------------------------
cv.namedWindow("Img")
cv.namedWindow("Edges")
Img=cv.imread("F:\\ImagesForTest\\BookPage.JPG",0)
res=CalcBlockMeanVariance(Img)
res=1.0-res
Img=np.float32(Img)/255
res=Img+res
cv.imshow("Img",Img);
_,res=cv.threshold(res,0.85,1,cv.THRESH_BINARY);
res=cv.resize(res,( int(res.shape[1]/2),int(res.shape[0]/2) ))
cv.imwrite("result.jpg",res*255);
cv.imshow("Edges",res)
cv.waitKey(0)