We are trying to deal with lots of Traditional Chinese documents ( scanned as images ). The result from tesseract is not good in default configs ( We are not familiar with tesseract training yet. ). So we tried to make a crowdsourcing website and invite people to provide identified text. The problem is that we need the bbox information extracted from tesseract using hocr config. But we don't need the OCR result. As the OCR process in Chinese is very slow. Is there anyway to get the bbox information directly without OCR process? ( either with tesseract or other tools ).
--- environments @ Ubuntu 13.10--- tesseract --version tesseract 3.02.01 leptonica-1.69 libgif 4.1.6 : libjpeg 8d : libpng 1.2.49 : libtiff 4.0.2 : zlib 1.2.8 --- kiang -- 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 http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/2f7abb1d-7f7b-4915-8256-af30c092fc39%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
