In case you did not binarize input image and you got strange output: ALLWAY check a thresholded image (GetThresholdedImage()) - see adapted you code and thresholdedImage.png
Zdenko On Mon, Oct 7, 2013 at 2:06 PM, Veerendra Jonnalagadda <[email protected] > wrote: > Hi > I have written simple code in C to extract text from Image. > But it is extracting only one line but I need all four lines to be > extrated.... > Please Help me.... > Regards > Veerendra > > #include<stdio.h> > #include<tesseract/baseapi.h> > #include<tesseract/strngs.h> > #include<leptonica/allheaders.h> > int main(int count, char** string) > { > int confidence; > char* text; > const char* lan="eng"; > const char* img_path; > if (count < 2) > { > printf("Empty path"); > return -1; > } > img_path=string[1]; > tesseract::TessBaseAPI* ocr = new tesseract::TessBaseAPI(); > printf("Tesseract-ocr version is %s\n", ocr->Version()); > printf("Leptonica version is %s\n", getLeptonicaVersion()); > if(ocr->Init(NULL, lan, tesseract::OEM_DEFAULT)) > { > printf("tesseract-ocr initialize error\n"); > return -1; > } > FILE* in = fopen(img_path, "rb"); > if (in == NULL) { > printf("can not open path ...\n"); > return -1; > } > fclose(in); > system("convert Playing.bmp Playing.tiff"); > Pix *img = pixRead("Playing.tiff"); > ocr->SetImage(img); > Boxa* box=ocr->GetComponentImages(tesseract::RIL_TEXTLINE,true,NULL,NULL); > printf("Number of Text Line is %d\n",box->n); > for (int z = 0; z < box->n; z++) > { > BOX* b = boxaGetBox(box, z, L_CLONE); > ocr->SetRectangle(b->x, b->y, b->w, b->h); > text = ocr->GetUTF8Text(); > confidence = ocr->MeanTextConf(); > printf("TEXT is %s\n",text); > } > pixDestroy(&img); > ocr->End(); > return 0; > } > > -- > -- > 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. > -- -- 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.
/*
* g++ test-2013-10-07.cpp -o test-2013-10-07 -llept -ltesseract
* ./test-2013-10-07 .
*/
#include<stdio.h>
#include<tesseract/baseapi.h>
#include<tesseract/strngs.h>
#include<leptonica/allheaders.h>
int main(int count, char** string)
{
int confidence;
char* text;
const char* lan="eng";
const char* img_path;
if (count < 2)
{
printf("Empty path\n");
return -1;
}
img_path=string[1];
tesseract::TessBaseAPI* ocr = new tesseract::TessBaseAPI();
printf("Tesseract-ocr version is %s\n", ocr->Version());
printf("Leptonica version is %s\n", getLeptonicaVersion());
if(ocr->Init(NULL, lan, tesseract::OEM_DEFAULT))
{
printf("tesseract-ocr initialize error\n");
return -1;
}
FILE* in = fopen(img_path, "rb");
if (in == NULL) {
printf("can not open path...\n");
return -1;
}
fclose(in);
//system("convert Playing.bmp Playing.tiff");
Pix *img = pixRead("Playing.tiff");
ocr->SetImage(img);
Pix *pix2 = ocr->GetThresholdedImage();
pixWrite("thresholdedImage.png", pix2, IFF_PNG);
pixDestroy(&pix2);
Boxa* box=ocr->GetComponentImages(tesseract::RIL_TEXTLINE,true,NULL,NULL);
printf("Number of Text Line is %d\n",box->n);
for (int z = 0; z < box->n; z++)
{
BOX* b = boxaGetBox(box, z, L_CLONE);
ocr->SetRectangle(b->x, b->y, b->w, b->h);
text = ocr->GetUTF8Text();
confidence = ocr->MeanTextConf();
printf("TEXT is %s\n",text);
}
pixDestroy(&img);
ocr->End();
return 0;
}
<<attachment: thresholdedImage.png>>
