image-table-ocr
image-table-ocr copied to clipboard
No way to get hocr of the image with the table_ocr library
We use the below config to get the table ocr, but there is no way to get hocr of the image. can someone add this feature please?
d = os.path.dirname(sys.modules["table_ocr"].__file__) tessdata_dir = os.path.join(d, "tessdata") tess_args = "--psm 6 -l table-ocr --tessdata-dir {0}".format(tessdata_dir)
Tidying up some old issues that haven't had activity for a long time.
Actually, I'll leave this open for a little longer in case someone wants to tackle this.
https://kba.github.io/hocr-spec/1.2/