A list of features to keep in mind as we consider which OCR engine to choose.

<br />

Options ordered from best to worst. More input needed. Need to also look through the list in Figure 6 of this paper containing OCR options: ://www.springerlink.com/content/mdxy1gtq3ba8d91t/fulltext.pdf

1. Novadys ://novadys.net/
   • Italian company with a free OCR service (one file at a time).
   • Seems pretty accurate.
   • Produces text and PDF output, among other formats.
   • Does not accept J2K format input.
2. Adobe acrobat Pro reader OCR
   • We have access to it.
   • BYU library has it.
   • That plus PDFBox gives us word bounding boxes and …
3. Omnipage
   • On library machines.
4. DocMorph ://docmorph.nlm.nih.gov/docmorph/docmorph.htm
   • From the US National Library of Medicine
   • Free
   • Seem to produce good quality OCR output on good images, pretty bad on other images.
   • Output is plain text. No apparent way to get token coordinates.
5. OcrTerminal.com ://www.ocrterminal.com/features/pricing.cgi
   • This is a OCR web service that is “powered by ABBYY” and prices range from 4 to 9 cents per page.
   • They are open to discussing academic prices.
   • They provide an API and also provide an XML output with bounding boxes, text line groupings of tokens, etc.
6. In-house PDFBox-based bounding box extraction code plus Abbyy retail product
   • Internal code project used to extract bounding boxes and OCR text from PDF files produced by Abbyy retail product.
   • Which is the cheapest edition of Abbyy FineReader that produces such PDF files?
   • Need to make sure we have access to zoning information in the PDF, especially lines. Aaron doesn't think it has zones, but does think it has lines.
   • No word/character confidence levels.
7. Ocropus
   • Open source
   • “Free”
   • Will likely require creating a large set of training data to get decent character recognition accuracies.
   • Can be made to output bounding boxes.
   • Outputs intermediate image segmentations and word hypothesis latices.
8. Abbyy Recognition Server
   • $1650+
   • Outputs bounding boxes and lots of other useful info.
   • High quality character recognition and zoning, etc.
   • Would the three labs and the library consider going in together on purchasing this?
9. Other OCR services for hire
   • Most seem expensive and/or do not provide bounding boxes.
10. Amazon Mechanical Turk
    • Transcription?
    • Bounding boxes?
11. Abbyy retail product
    • $600
    • May or may not output bounding boxes and very little else.
12. Cuneiform
13. Bill’s voting engine
14. Ancestry's Scanning Service
    • Not sure if they offer a relatively cheap OCR service that might be cheaper than buying ARS.
    • After asking Shawn Reid we know that Ancestry has discontinued their digitization service.

<br />

1. Multivalent Extract Text
   • Has a stand-alone tool to extract text along with bounding boxes.
   • Extract Text Documentation Page: ://multivalent.sourceforge.net/Tools/doc/ExtractText.html
   • Package website: ://multivalent.sourceforge.net/
   • Downloads: ://multivalent.sourceforge.net/download.html
2. PDFBox
   • Library, not a stand-alone tool?
3. Apache Tika
   • Not sure if this can extract bounding boxes.
   • ://tika.apache.org/0.7/gettingstarted.html
4. PDFTOHTML
   • ://pdftohtml.sourceforge.net/

<br />