try the latest code: there was fix regarding bbox after releasing tesseract 4.0
Zdenko št 20. 6. 2019 o 14:16 Arno Loo <[email protected]> napísal(a): > Hello, > > I have a recurrent problem and I don't understand why it is happening : > for many of the documents I have, Tesseract's hocr output is giving > incoherent bbox for a few ocrx_word. These ocrx_words are always composed > of a single character and their bbox takes the entire page, which is weird > because these ocrx_words are part of ocr_lines which have correct bboxes. > > In the example I provided, the ocrx_word is an error as it detects the > line from the table as a |. But in most cases, the character read in the > word is correct, only its bbox is wrong. > > Is anyone knows why it is happening and how I could fix it ? > > The parameters I use are nothing fancy : > tesseract input.jpg output -l eng -c tessedit_create_hocr=1 > > Thank you. > > -- > 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/51affae0-665e-408c-a7d9-de47b6cbf9e7%40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/51affae0-665e-408c-a7d9-de47b6cbf9e7%40googlegroups.com?utm_medium=email&utm_source=footer> > . > For more options, visit https://groups.google.com/d/optout. > -- 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/CAJbzG8whb8wBjsgfoYNuJNjW0Af3kqUb9WqO74REJEF9yj3feQ%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
