extracting numbers from Bitmap in android using tess-two library

问题

I want to extract a number from a Bitmap. I'm using the tess-two library, but it does not recognize correctly.

Example Code:

    @Override
        public void onClick(View v) {
        switch (v.getId()){
        case R.id.b2:
        InputStream is = null;
        try {
        is = getApplicationContext().getAssets().open("zak.jpeg");
        } catch (IOException e1) {
        e1.printStackTrace();
        }
         final Drawable drw = Drawable.createFromStream(is, null);
         bmp = ((BitmapDrawable) drw).getBitmap();

        TessBaseAPI baseApi = new TessBaseAPI();
           bmp =BITMAP_RESIZER(bmp,bmp.getWidth(),bmp.getHeight());
            bmp =convertToGrayscale(bmp);
             bmp =RemoveNoise(bmp);
             iv.setImageBitmap(bmp);

          baseApi.init("/mnt/sdcard/Download/", "eng");
          baseApi.setVariable(TessBaseAPI.VAR_CHAR_WHITELIST,"1234567890");
          baseApi.setVariable(TessBaseAPI.VAR_CHAR_BLACKLIST,"!@#$%^&*   ()_+=-[]}{" +";:'\"\\|~`,./<>?");
          baseApi.setDebug(true);
         baseApi.setImage(bmp);

        String recognizedText = baseApi.getUTF8Text();
        tv.setText(" numbers : "+recognizedText.trim());
        Log.d("karim", recognizedText);
        baseApi.end();
             break;

Method to convert the Bitmap to grayscale:

 public static Bitmap convertToGrayscale(Bitmap bmpOriginal) {
          int width, height;
           height = bmpOriginal.getHeight();
          width = bmpOriginal.getWidth();    

         Bitmap bmpGrayscale = Bitmap.createBitmap(width, height,  Bitmap.Config.ARGB_8888);
         Canvas c = new Canvas(bmpGrayscale);
         Paint paint = new Paint();
         ColorMatrix cm = new ColorMatrix();
         cm.setSaturation(0);
         ColorMatrixColorFilter f = new ColorMatrixColorFilter(cm);
         paint.setColorFilter(f);
         c.drawBitmap(bmpOriginal, 0, 0, paint);
         return bmpGrayscale;
     }

Method to remove the noise from the Bitmap:

  public Bitmap RemoveNoise(Bitmap bmap) {
        for (int x = 0; x < bmap.getWidth(); x++) {
        for (int y = 0; y < bmap.getHeight(); y++) {
        int pixel = bmap.getPixel(x, y);
        int R = Color.red(pixel);
        int G = Color.green(pixel);
        int B = Color.blue(pixel);
        if (R < 162 && G < 162 && B < 162)
        bmap.setPixel(x, y, Color.BLACK);
        }
    }
        for (int  x = 0; x < bmap.getWidth(); x++) {
        for (int y = 0; y < bmap.getHeight(); y++) {
        int pixel = bmap.getPixel(x, y);
        int R = Color.red(pixel);
        int G = Color.green(pixel);
        int B = Color.blue(pixel);
        if (R > 162 && G > 162 && B > 162)
              bmap.setPixel(x, y, Color.WHITE);
        }
    }
       return bmap;
    }

Method to resize the bitmap:

   public Bitmap BITMAP_RESIZER(Bitmap bitmap,int newWidth,int newHeight) 
      {    
    Bitmap scaledBitmap = Bitmap.createBitmap(newWidth, newHeight, Config.ARGB_8888);

    float ratioX = newWidth / (float) bitmap.getWidth();
    float ratioY = newHeight / (float) bitmap.getHeight();
    float middleX = newWidth / 2.0f;
    float middleY = newHeight / 2.0f;

    Matrix scaleMatrix = new Matrix();
    scaleMatrix.setScale(ratioX, ratioY, middleX, middleY);

    Canvas canvas = new Canvas(scaledBitmap);
    canvas.setMatrix(scaleMatrix);
    canvas.drawBitmap(bitmap, middleX - bitmap.getWidth() / 2, middleY - bitmap.getHeight() / 2, new Paint(Paint.FILTER_BITMAP_FLAG));

    return scaledBitmap;

    }

How do I fix this problem?

回答1:

Maybe this is somewhat late but anyways if I understand correctly what you want is only numbers as output.

The whitelist you provided is okay but tesseract will forcefully match the letters to the numbers specified in the whitelist. There is no way to make it omitt certain characters,but what you could do is set the whitelist for the whole alphabet and then manually separate letters from numbers in your code.

回答2:

baseApi.SetVariable("tessedit_char_whitelist", "0123456789");

来源：https://stackoverflow.com/questions/34755076/extracting-numbers-from-bitmap-in-android-using-tess-two-library

标签

android

ocr

tess-two