Thanks. Is there any idea how to change code to get font information by
LSTM.
On Wednesday, 13 September 2017 18:52:22 UTC+5:30, Supriya Das wrote:
>
> *Hi All,*
>
> *When i am trying to get information of word wise font attributes not
> getting result. I choose ocr engine as a OEM_LSTM_ONLY. If i
> choose OEM_TESSERACT_ONLY then getting correct result. Please suggest.
> Thanks in advance. *
>
>
> tesseract::TessBaseAPI *api = new tesseract::TessBaseAPI();
> // Initialize tesseract-ocr with English, without specifying tessdata path
> if(api->Init(NULL, "eng", tesseract::OEM_LSTM_ONLY)) {
> fprintf(stderr, "Could not initialize tesseract.\n");
> exit(1);
> }
> //api->SetVariable("save_blob_choices", "T");
>
> //api->SetVariable("tessedit_char_whitelist","0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ./-");
> //api->SetVariable("tessedit_ocr_engine_mode","10");
> api->SetPageSegMode(tesseract::PSM_AUTO_ONLY);
> api->SetVariable("chop_enable", "1");
> api->SetImage((uchar*)Result.data,Result.cols,Result.rows,1,Result.cols);
>
>
> time(& Start);
> char* out = api->GetUTF8Text();
> time(& End);
> Result.release();
> dif = difftime(End,Start);
> printf("\nTesseract Processing Time %lf\n",dif);
> // Tesseract bounding box finding Word Wise
> time(& Start);
> tesseract::ResultIterator* ri = api->GetIterator();
> char* word;
> const char *font_name;
> bool bold, italic, underlined, monospace, serif, smallcaps;
> int pointsize, font_id;
> if(ri != 0){
> do{
> //tesseract::Orientation orientation;
> //tesseract::WritingDirection writing_direction;
> //tesseract::TextlineOrder textline_order;
> //float deskew_angle;
>
>
> //ri->Orientation(&orientation,&writing_direction,&textline_order,&deskew_angle);
> word = ri->GetUTF8Text(tesseract::RIL_WORD);
>
> if(word != 0 && word[0] != '\0' && word[1] != ' ' && word[0] != ' '){
> float conf = ri->Confidence(tesseract::RIL_WORD);
> int x1, y1, x2, y2;
> if(conf > 0)
> {
> font_name = ri->WordFontAttributes(&bold, &italic, &underlined,
> &monospace, &serif,
> &smallcaps, &pointsize,
> &font_id);
> ri->BoundingBox(tesseract::RIL_WORD, &x1, &y1, &x2, &y2);
> fprintf(fpout,"%s %d %d %d %d %d %d %d %d %d %d %d %d %s\n",word, x1, y1,
> x2,
> y2,pointsize,bold,italic,underlined,monospace,serif,smallcaps,font_id,font_name);
> }
> }
> } while((ri->Next(tesseract::RIL_WORD)));
> }
>
>
--
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].
To post to this group, send email to [email protected].
Visit this group at https://groups.google.com/group/tesseract-ocr.
To view this discussion on the web visit
https://groups.google.com/d/msgid/tesseract-ocr/abe274d2-f6b2-499a-bcb2-468a72804970%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.
