EpubCCCan a scanned PDF become a reflowable EPUB?
Updated:
A scanned PDF can become a reflowable EPUB only after OCR turns each page image into text, and that text carries OCR errors on poor or old scans. EpubCC does not offer OCR yet; it converts PDFs that already have selectable text.
What a scanned PDF is
Each page is a photograph of paper. Some scans include a hidden OCR text layer, which is why you can sometimes select text in them; its quality depends on the scan and the software that made it.
What our benchmark shows about scans
Our corpus includes an 1867 printing of Alice's Adventures in Wonderland scanned by the University of Toronto. Every engine was measured on its existing OCR layer, against a different edition of the text, so the scores are low for everyone and are not a measure of OCR itself.
Evidence from the benchmark
| Engine | 8-gram recall |
|---|---|
| EpubCC engine (EPUB output) | 0.767 |
| EpubCC engine (plain text) | 0.765 |
| pdf_oxide · extract_text | 0.726 |
| pdf_oxide · to_plain_text (XY-cut) | 0.658 |
| pdf_oxide · Markdown | 0.653 |
| PDFium · text().all() | 0.746 |
| OpenDataLoader PDF (local mode) | 0.749 |
| pdftotext (Poppler) | 0.743 |
| Document | EpubCC engine (EPUB output) | EpubCC engine (plain text) | pdf_oxide · extract_text | pdf_oxide · to_plain_text (XY-cut) | pdf_oxide · Markdown | PDFium · text().all() | OpenDataLoader PDF (local mode) | pdftotext (Poppler) |
|---|---|---|---|---|---|---|---|---|
| Alice's Adventures in Wonderland, 1867 printing (scan, Internet Archive) | 0.513 | 0.494 | 0.632 | 0.639 | 0.524 | 0.651 | 0.625 | 0.156 |
Convert a PDF with selectable text
Convert up to 5 pages free, no account needed.