ocrodjvu | tool to perform OCR on DjVu documents | Mehr ... |
ocrodjvu is a wrapper around OCR systems (OCRopus+Tesseract and Cuneiform) with the purpose to perform Optical Character Recognition (OCR) in documents in DjVu format (which is especially suited for archival of books with high quality). . When a DjVu document has been OCRed, it includes a text version of the images of the scanned document and, with common programs, one can not only print on paper, but also read such books/documents, searching for specific terms and also use the information in the OCR layer as a way to higher the accessibility of such documents. |