<https://lh6.googleusercontent.com/-gFboadFkrOM/Uk6dz2WI7rI/AAAAAAAAATs/2aWZloPX_T0/s1600/texto.jpg>
Hi I' ve been trying to fix the code and now I read some text but the text
readed is not correct. When I' m trying to read the image, "texto.jpg" the
output text is something like that:
II" n llfi ' IIIi"'"“MM“ufimn"w»“W,;H»m““wu%M%“m»%.IlI!!!!!| "" "" ''"umm
""""'"""“ "" "" '''''|IImmw '!!!ll::...i!!"!""' W*WM‘WM
Anybody knows what is the reason of that?
This is the image to read:
El viernes, 4 de octubre de 2013 08:59:34 UTC+2, adrian company escribió:
>
> Hi all,
> I am using tesseract engine to detect text from an image. I process the
> image to binarize it and then extract text from it, but some errors are
> displayed when I execute the program.
> Does anyone know what I am doing wrong? I paste the code and errors
> displayed in the execution.
>
> if (waitKey(10) >= 0){
>
> // leer imagen
> Mat imagen = imread(
> "/home/adrian/workspace/OCR/matricula2.jpg"/*,CV_LOAD_IMAGE_GRAYSCALE*/);
> imshow("imagen",imagen);
>
>
> //procesamos imagen redimensionada: (filtramos, pasamos a
> escala grises, binarizamos)
> medianBlur(imagen,imagen, 3);
> cvtColor(imagen,imagen,CV_BGR2GRAY);
> threshold(imagen,imagen,umbral, umbral_max,3);
>
> // inicializamos motor OCR tesseract
> putenv("TESSDATA_PREFIX=/usr/local/share/");
> setlocale(LC_NUMERIC, "C");
> tesseract::TessBaseAPI api;
> printf("\nTesseract-ocr version: %s--------\t",api.
> Version()); //version de tesseract
> printf("Leptonica version: %s\n", getLeptonicaVersion
> ()); //version de leptonica
> printf(
> "___________________________________________________________________________\n"
> );
>
> if (api.Init(NULL, "spa")) { //idioma
> spanish
> fprintf( stderr, " ¡No se pudo inicializar
> tesseract! \n" );
> exit(1);
> }
>
> api.SetPageSegMode(tesseract::PSM_AUTO);
> api.SetVariable("tessedit_char_whitelist",
> "ABCDEFGHIJKLMNOPQRSTUVWXYZ.0123456789");
>
> api.SetImage(imagen.data, imagen.size().width,imagen.
> size().height, imagen.channels(), imagen.step1());
>
> // region de interes (ROI), p.ej. regiones que contengan texto
> Rect textROI(0,0,imagen.cols,imagen.rows);//imagen completa
>
>
> // recognize text
> api.TesseractRect( imagen.data, 0,imagen.step1(),
> textROI.x,textROI
> .y,textROI.width, textROI.height);
>
> char *texto = new char[200];
> texto = api.GetUTF8Text();
> // remove "newline"
> string t1(texto);
> t1.erase( remove(t1.begin(), t1.end(), '\n'), t1.end() );
>
> // print found text
> printf("TEXTO LEIDO: \n");
> printf( "%s",t1.c_str() );
>
>
>
> // draw rectangle image
>
> rectangle(imagen, textROI, Scalar(0, 0, 255), 2, 8, 0);
>
> imwrite("/home/adrian/workspace/OCR/procesadas/binaria.jpg",
> imagen);
>
> imshow("binarizada",imagen);
>
> delete [] texto;
> // destroy tesseract OCR engine
> api.Clear();
> api.End();
> }
>
> and the errors displayed are:
>
> Tesseract-ocr version: 3.02.02-------- Leptonica version: leptonica-1.69
> ___________________________________________________________________________
> Error in pixReduceRankBinary2: hs must be at least 2
> Error in pixDilateBrick: pixs not defined
> Error in pixExpandReplicate: pixs not defined
> Error in pixAnd: pixs1 not defined
> Error in pixDilateBrick: pixs not defined
> Error in pixExpandReplicate: pixs not defined
> Error in pixAnd: pixs2 not defined
> TEXTO LEIDO:
>
>
>
>
>
>
--
--
You received this message because you are subscribed to the Google
Groups "tesseract-ocr" group.
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to
[email protected]
For more options, visit this group at
http://groups.google.com/group/tesseract-ocr?hl=en
---
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/groups/opt_out.
