Closed catabre closed 4 years ago
Modified the gcv2hocr.py to parse the fullTextAnnotation block and accordingly generate a rich hocr file having ocr_page ocr_carea ocr_par ocr_line ocrx_word tags.
Thank you for your commit !
Modified the gcv2hocr.py to parse the fullTextAnnotation block and accordingly generate a rich hocr file having ocr_page ocr_carea ocr_par ocr_line ocrx_word tags.