ocrodjvu is a wrapper for OCR systems that allows you to perform OCR on DjVu files.
| Tags | multimedia Graphics Graphics Conversion Text Processing |
|---|---|
| Licenses | GPLv2 |
| Operating Systems | POSIX Linux |
| Implementation | Python |
Recent releases


Release Notes: Error handling was improved.


Release Notes: For Tesseract ≥ 3.00, bounding boxes of particular characters are now extracted with higher accuracy. An option to use an HTML 5 parser was added.


Release Notes: For Tesseract 3.0, bounding boxes of particular characters are extracted with higher accuracy.


Release Notes: A bug in djvu2hocr, which made it produce upside-down hOCR, was fixed.


Release Notes: Compatibility with Tesseract 3.00 was fixed.