All geek questions in one place

OpenCV for OCR: How to Calculate Threshold Levels for an OCR Gray Image

I am trying to prepare images for OCR, and so far this is what I have done using information from Extracting OpenCV Text

From the resulting image, I use the outlines that were filtered to make the mask as follows:

//this is the mask of all the text
Mat maskF = Mat::zeros(rgb.rows, rgb.cols, CV_8UC1);
// CV_FILLED fills the connected components found - CV_FILLED to fill
drawContours(maskF, letters, -1, Scalar(255), CV_FILLED);
cv::imwrite("noise2-Mask.png", maskF);

The resulting img is promising: enter image description here

considering this was my original img: enter image description here

Unfortunately, when running Tesseract it has some problems, I think that the gray levels that you see between the letters in words mix tesseract - so you think, yes, let's do a binary conversion, well, that just skips the second half, therefore, I also tried applying the Otsu threshold, but the text becomes jagged and the characters lose their shape.

CalcBlockMeanVariance OpenCV Adaptive Threshold OCR, ( , tbh)

res=1.0-res;
res=Img+res;

, - , ! , Tesseract, , , , reco)

+2
2

  • , . . :

    / ( , ). , , , . 8x8 . avg . ( ) .

    , . . , .

    ++ :

    color picture::normalize(int sz,bool _recolor,bool _sbstract)
    {
    struct _cell { color col; int a[4],da,_paper; _cell(){}; _cell(_cell& x){ *this=x; }; ~_cell(){}; _cell* operator = (const _cell *x) { *this=*x; return this; }; /*_cell* operator = (const _cell &x) { ...copy... return this; };*/ };
    int i,x,y,tx,ty,txs,tys,a0[4],a1[4],n,dmax;
    int x0,x1,y0,y1,q[4][4][2],qx[4],qy[4];
    color c;
    _cell **tab;
    // allocate grid table
    txs=xs/sz; tys=ys/sz; n=sz*sz; c.dd=0;
    if ((txs<2)||(tys<2)) return c;
    tab=new _cell*[tys]; for (ty=0;ty<tys;ty++) tab[ty]=new _cell[txs];
    // compute grid table
    for (y0=0,y1=sz,ty=0;ty<tys;ty++,y0=y1,y1+=sz)
     for (x0=0,x1=sz,tx=0;tx<txs;tx++,x0=x1,x1+=sz)
        {
        for (i=0;i<4;i++) a0[i]=0;
        for (y=y0;y<y1;y++)
         for (x=x0;x<x1;x++)
            {
            dec_color(a1,p[y][x],pf);
            for (i=0;i<4;i++) a0[i]+=a1[i];
            }
        for (i=0;i<4;i++) tab[ty][tx].a[i]=a0[i]/n;
        enc_color(tab[ty][tx].a,tab[ty][tx].col,pf);

        tab[ty][tx].da=0;
        for (i=0;i<4;i++) a0[i]=tab[ty][tx].a[i];
        for (y=y0;y<y1;y++)
         for (x=x0;x<x1;x++)
            {
            dec_color(a1,p[y][x],pf);
            for (i=0;i<4;i++) tab[ty][tx].da+=abs(a1[i]-a0[i]);
            }
        tab[ty][tx].da/=n;
        }
    // compute max safe delta dmax = avg(delta)
    for (dmax=0,ty=0;ty<tys;ty++)
     for (tx=0;tx<txs;tx++)
      dmax+=tab[ty][tx].da;
       dmax/=(txs*tys);

    // select paper cells and compute avg paper color
    for (i=0;i<4;i++) a0[i]=0; x0=0;
    for (ty=0;ty<tys;ty++)
     for (tx=0;tx<txs;tx++)
      if (tab[ty][tx].da<=dmax)
        {
        tab[ty][tx]._paper=1;
        for (i=0;i<4;i++) a0[i]+=tab[ty][tx].a[i]; x0++;
        }
      else tab[ty][tx]._paper=0;
    if (x0) for (i=0;i<4;i++) a0[i]/=x0;
    enc_color(a0,c,pf);
    // remove saturated ink cells from paper (small .da but wrong .a[])
    for (ty=1;ty<tys-1;ty++)
     for (tx=1;tx<txs-1;tx++)
      if (tab[ty][tx]._paper==1)
       if ((tab[ty][tx-1]._paper==0)
         ||(tab[ty][tx+1]._paper==0)
         ||(tab[ty-1][tx]._paper==0)
         ||(tab[ty+1][tx]._paper==0))
        {
        x=0; for (i=0;i<4;i++) x+=abs(tab[ty][tx].a[i]-a0[i]);
        if (x>dmax) tab[ty][tx]._paper=2;
        }
    for (ty=0;ty<tys;ty++)
     for (tx=0;tx<txs;tx++)
      if (tab[ty][tx]._paper==2)
       tab[ty][tx]._paper=0;

    // piecewise linear interpolation H-lines
    int ty0,ty1,tx0,tx1,d;
    if (_sbstract) for (i=0;i<4;i++) a0[i]=0;
    for (y=0;y<ys;y++)
        {
        ty=y/sz; if (ty>=tys) ty=tys-1;
        // first paper cell
        for (tx=0;(tx<txs)&&(!tab[ty][tx]._paper);tx++); tx1=tx;
        if (tx>=txs) continue; // no paper cell found
        for (;tx<txs;)
            {
            // fnext paper cell
            for (tx++;(tx<txs)&&(!tab[ty][tx]._paper);tx++);
            if (tx<txs)
                {
                tx0=tx1; x0=tx0*sz;
                tx1=tx;  x1=tx1*sz;
                d=x1-x0;
                }
            else x1=xs;

            // interpolate
            for (x=x0;x<x1;x++)
                {
                dec_color(a1,p[y][x],pf);
                for (i=0;i<4;i++) a1[i]-=tab[ty][tx0].a[i]+(((tab[ty][tx1].a[i]-tab[ty][tx0].a[i])*(x-x0))/d)-a0[i];
                if (pf==_pf_s   ) for (i=0;i<1;i++) clamp_s32(a1[i]);
                if (pf==_pf_u   ) for (i=0;i<1;i++) clamp_u32(a1[i]);
                if (pf==_pf_ss  ) for (i=0;i<2;i++) clamp_s16(a1[i]);
                if (pf==_pf_uu  ) for (i=0;i<2;i++) clamp_u16(a1[i]);
                if (pf==_pf_rgba) for (i=0;i<4;i++) clamp_u8 (a1[i]);
                enc_color(a1,p[y][x],pf);
                }
            }
        }

    // recolor paper cells with avg color (remove noise)
    if (_recolor)
     for (y0=0,y1=sz,ty=0;ty<tys;ty++,y0=y1,y1+=sz)
      for (x0=0,x1=sz,tx=0;tx<txs;tx++,x0=x1,x1+=sz)
       if (tab[ty][tx]._paper)
        for (y=y0;y<y1;y++)
         for (x=x0;x<x1;x++)
          p[y][x]=c;

    // free grid table
    for (ty=0;ty<tys;ty++) delete[] tab[ty]; delete[] tab;
    return c;
    }

    . . <0,765> pic1.normalize(8,false,true);

    normalize

  • Binarize

    tresholding, , (R, G, B) <min,max>, c1 else c0:

    void picture::treshold_AND(int min,int max,int c0,int c1) // all channels tresholding: c1 <min,max>, c0 (-inf,min)+(max,+inf)
    {
    int x,y,i,a[4],e;
    for (y=0;y<ys;y++)
     for (x=0;x<xs;x++)
        {
        dec_color(a,p[y][x],pf);
        for (e=1,i=0;i<3;i++) if ((a[i]<min)||(a[i]>max)){ e=0; break; }
        if (e) for (i=0;i<4;i++) a[i]=c1;
         else  for (i=0;i<4;i++) a[i]=c0;
        enc_color(a,p[y][x],pf);
        }
    }

    pic1.treshold_AND(0,127,765,0); RGBA :

    binarise

    JPEG (PNG ). , .

    , . ( ), , . , , , . :

    bimodal histogram

    , ( / ), . ( ), // ( ), , , , .

+2

, tophat , ! ! adaptiveThreshold?

0

Source: https://habr.com/ru/post/1669238/

More articles:


All Articles