My goal is to turn a physical book into a virtual book that will be reflowable on whatever device I like, or into a PDF that is customized for my particular device. Here are the steps involved in making that happen:
1. Scan book using DIY Book Scanner
2. Postprocess images to undistorted, cleaned up images (PostProcessor software)
3. OCR (ABBYY FineReader)
4. Spellcheck, correct various other nonspelling errors (in ABBYY FineReader)
5. Export to PDF (ABBYY FineReader)
6. Extract data and convert to reflowable format (then a miracle occurs)
7. Convert to desired format (PDF or MOBI)
Right now I'm working on step 6...
My book processing workflow
Moderator: peterZ
- rob
- Posts: 773
- Joined: 03 Jun 2009, 13:50
- E-book readers owned: iRex iLiad, Kindle 2
- Number of books owned: 4000
- Country: United States
- Location: Maryland, United States
- Contact:
My book processing workflow
The Singularity is Near. ~ http://halfbakedmaker.org ~ Follow me as I build the world's first all-mechanical steam-powered computer.
- rob
- Posts: 773
- Joined: 03 Jun 2009, 13:50
- E-book readers owned: iRex iLiad, Kindle 2
- Number of books owned: 4000
- Country: United States
- Location: Maryland, United States
- Contact:
Re: My book processing workflow
I should mention that the step 6 I'm working on will only work for single-column text. I'm not quite up to detecting multi-column text.
The Singularity is Near. ~ http://halfbakedmaker.org ~ Follow me as I build the world's first all-mechanical steam-powered computer.