Hello,
I attached a cpp file which i tried something with it. It is not a tidy
code but i think you can find some clues on how to use api directory of
tesseract.
Below is the console command on linux that i use to compile this cpp file
g++ deneme234.cpp -I /usr/include/opencv -L/usr/lib
-L/usr/lib/pyshared/python2.7/opencv -lcxcore -lcv -lhighgui -lcvaux -I
/usr/include -I /usr/local/include/leptonica -I /usr/include/leptonica -I
/usr/local/include -I /usr/local/include/tesseract -L/usr/local/lib -I ./
-ltesseract_api -ltesseract_textord -ltesseract_main -ltesseract_wordrec
-ltesseract_classify -ltesseract_dict -ltesseract_viewer -ltesseract_ccutil
-ltesseract_ccstruct -ltesseract_cutil -ltesseract_image -ltiff -lpthread
-L ./ -g -O0 -o deneme2346
2011/11/13 zdenko podobny <[email protected]>
>
>
> On Sun, Nov 13, 2011 at 5:32 AM, cyrt <[email protected]> wrote:
>
>> Could someone please explain how I can use tesseract in c++?
>
>
> use api/tesseractmain.cpp api/tesseractmain.h as example
>
>> I
>> downloaded the source files via svn and compiled the solution. Which
>> libraries do I now have to link and where do I find an include
>> directory containing all necessary header files?
>>
> officially there is no windows library solution yet.
>
> But have a look at developer forum - there are information with proposed
> solution for library on windows.
>
>>
>> --
>> 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 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 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
#include "deneme234.h"
#include "cvdeneme2.h"
int mainOfTesseract(const char* langString, const char*imageString, const char* outputString, const char* datapathString) {
#ifdef USE_NLS
setlocale (LC_ALL, "");
bindtextdomain (PACKAGE, LOCALEDIR);
textdomain (PACKAGE);
#endif
char **argv={};
// Make the order of args a bit more forgiving than it used to be.
const char* lang = "eng";
const char* image = NULL;
const char* output = NULL;
const char* datapath=NULL;
tesseract::PageSegMode pagesegmode = tesseract::PSM_SINGLE_CHAR;
lang = langString;
image = imageString;
output = outputString;
datapath=datapathString;
tesseract::TessBaseAPI api;
api.SetOutputName(output);
api.Init(datapath, lang, tesseract::OEM_DEFAULT,
&(argv[0]), 0, NULL, NULL, false);
// We have 2 possible sources of pagesegmode: a config file and
// the command line. For backwards compatability reasons, the
// default in tesseract is tesseract::PSM_SINGLE_BLOCK, but the
// default for this program is tesseract::PSM_AUTO. We will let
// the config file take priority, so the command-line default
// can take priority over the tesseract default, so we use the
// value from the command line only if the retrieved mode
// is still tesseract::PSM_SINGLE_BLOCK, indicating no change
// in any config file. Therefore the only way to force
// tesseract::PSM_SINGLE_BLOCK is from the command line.
// It would be simpler if we could set the value before Init,
// but that doesn't work.
//if (api.GetPageSegMode() == tesseract::PSM_SINGLE_BLOCK)
api.SetPageSegMode(pagesegmode);
FILE* fin = fopen(image, "rb");
if (fin == NULL) {
printf("Cannot open input file: %s\n", image);
exit(2);
}
fclose(fin);
PIX *pixs;
if ((pixs = pixRead(image)) == NULL) {
printf("Unsupported image type.\n");
exit(3);
}
pixDestroy(&pixs);
STRING text_out;
/*bool TessBaseAPI::ProcessPage(Pix* pix, int page_index, const char* filename,
const char* retry_config, int timeout_millisec,
STRING* text_out) {
bool TessBaseAPI::ProcessPages(const char* filename,
const char* retry_config, int timeout_millisec,
STRING* text_out) {
*/
if (!api.ProcessPages(image, NULL, 0, &text_out)) {
printf("Error during processing.\n");
}
tesseract::ResultIterator* ri=api.GetIterator();
Pix* pixa=(*ri).GetBinaryImage(tesseract::RIL_SYMBOL);
printf("%d",(pixa[1]).data);
(*ri).Begin();
printf("-----%s",(*ri).GetUTF8Text(tesseract::RIL_SYMBOL));
tesseract::ChoiceIterator* ci=new tesseract::ChoiceIterator(*ri);
(*ci).Next();
const char *txt=(ci)->GetUTF8Text();
printf("-----%s",(txt));
STRING outfile = output;
outfile += ".txt";
FILE* fout = fopen(outfile.string(), "wb");
if (fout == NULL) {
printf("Cannot create output file %s\n", outfile.string());
exit(1);
}
fwrite(text_out.string(), 1, text_out.length(), fout);
fclose(fout);
return 0; // Normal exit
};
int pixsOfOneWord(const char* langString, const char*imageString, Pix *outputData, const char* datapathString) {
#ifdef USE_NLS
setlocale (LC_ALL, "");
bindtextdomain (PACKAGE, LOCALEDIR);
textdomain (PACKAGE);
#endif
char **argv={};
const char* lang = "eng";
const char* image = NULL;
const char* datapath=NULL;
tesseract::PageSegMode pagesegmode = tesseract::PSM_SINGLE_CHAR;
lang = langString;
image = imageString;
datapath=datapathString;
tesseract::TessBaseAPI api;
api.Init(datapath, lang, tesseract::OEM_DEFAULT,&(argv[0]), 0, NULL, NULL, false);
api.SetPageSegMode(pagesegmode);
/*
FILE* fin = fopen(image, "rb");
if (fin == NULL) {
printf("Cannot open input file: %s\n", image);
exit(2);
}
fclose(fin);
PIX *pixs;
if ((pixs = pixRead(image)) == NULL) {
printf("Unsupported image type.\n");
exit(3);
}
pixDestroy(&pixs);
STRING text_out;
if (!api.ProcessPages(image, NULL, 0, &text_out)) {
printf("Error during processing.\n");
}
*/
IplImage* img=0;
img=cvLoadImage("paket2copy.png");
printf("width:%d",img->width);
printf("byte depth:%d",img->depth/8);
printf("widthStep:%d",img->widthStep);
api.SetImage((uchar*)img->imageData,img->width,img->height,img->depth/8,img->widthStep);
api.SetRectangle(0,0,img->width, img->height);
int left,top,right,bottom;
left=0;top=0;right=0;bottom=0;
api.Recognize(NULL);
tesseract::ResultIterator *ri=api.GetIterator();
tesseract::ChoiceIterator *choiceItr;
const tesseract::ResultIterator itr = *ri;
choiceItr = new tesseract::ChoiceIterator(itr);
const char * out=choiceItr->GetUTF8Text();
char * out2=(*ri).GetUTF8Text(tesseract::RIL_SYMBOL);
if((*ri).BoundingBox(tesseract::RIL_SYMBOL,&left,&top,&right,&bottom))
{printf("bb dogru\n");printf("%d,%d,%d,%d",left,top,right,bottom);}
printf("out:%s,out2:%s",out,out2);
//pixDestroy(&pixa);
printf("buraya da geldi...\n");
cvNamedWindow("mainWin", CV_WINDOW_AUTOSIZE);
cvMoveWindow("mainWin", img->width,img->height);
printf("buraya da geldi........\n");
// show the image
cvShowImage("mainWin", img );
// wait for a key
cvWaitKey(0);
// release the image
cvReleaseImage(&img );
return 0; // Normal exit
};
/*int main(){
mainOfTesseract("klm","adsizue.tif","outputcikti",".");
return 0;
};*/
int main()
{
IplImage* img = 0;
int height,width,step,channels;
uchar *data;
int i,j,k;
Pix* pixa;
pixsOfOneWord("klm", "paket2.tif", pixa, ".");
//img=cvCreateImage(cvSize((int)pixa[0].w,(int)pixa[0].h),IPL_DEPTH_8U,1);
// get the image data
/*height = img->height;
width = img->width;
step = img->widthStep;
channels = img->nChannels;
data = (uchar *)img->imageData;
printf("Processing a %dx%d image with %d channels\n",height,width,channels);
*/
// create a window
//cvNamedWindow("mainWin", CV_WINDOW_AUTOSIZE);
//cvMoveWindow("mainWin", (int)pixa[0].w,(int)pixa[0].h);
/*
// invert the image
for(i=0;i<height;i++) for(j=0;j<width;j++) for(k=0;k<channels;k++)
data[i*step+j*channels+k]=255-data[i*step+j*channels+k];
*/
// show the image
//cvShowImage("mainWin", img );
// wait for a key
//cvWaitKey(0);
// release the image
//cvReleaseImage(&img );
return 0;
};
