Wikipedia:Articles for deletion/Ocropus

From Wikipedia, the free encyclopedia

The following discussion is an archived debate of the proposed deletion of the article below. Please do not modify it. Subsequent comments should be made on the appropriate discussion page (such as the article's talk page or in a deletion review). No further edits should be made to this page.

The result was keep. bibliomaniac15 BUY NOW! 20:10, 5 July 2007 (UTC)

[edit] Ocropus

Ocropus (edit|talk|history|links|watch|logs) – (View log)

Non-notable pre-alpha software. —Psychonaut 20:45, 29 June 2007 (UTC)

  • Delete Wikipedia is not a crystal ball Rackabello 21:05, 29 June 2007 (UTC)
  • Delete but best wishes for the developer (a colleague of mine)—let's hope Ocropus is one day notable enough to be encyclopedic! :) —Psychonaut 21:12, 29 June 2007 (UTC)
  • Delete. Not notable software; crystal balling. -- Mikeblas 14:28, 30 June 2007 (UTC)
  • Delete per nom. JJL 21:31, 30 June 2007 (UTC)
  • Keep: Google and the German University of Kaiserslautern are sponsoring its development. It's usable software right now; I run it on Ubuntu Feisty Fawn (Linux). 128.158.145.51 19:11, 2 July 2007 (UTC)
It's received coverage from Slashdot[1], Linux.com[2], and Ars Technica[3] among others. OCRopus is part of Google's Book scanning project. 128.158.145.51 19:25, 2 July 2007 (UTC)
  • Keep. Googling "OCRopus OCR" gets 165,000 hits and there's a Digg story on it. The article could use some rewording in places, but it's a good article about a real software product. I don't see anything wrong with it. TMC1221 22:40, 2 July 2007 (UTC)
  • Keep. It's no crystal balling - it's already useable. And it's the best free software solution of it's kind, I think. The only thing that is useful for me on Linux. --Speck-Made 23:12, 2 July 2007 (UTC)

A couple of things:

  • The codebase is actually quite mature as is; it's called "pre-alpha" because (1) there are going to be significant (specific, known) API changes over the next 3-6 months, and (2) the project wants developers and contributors right now, not a lot of end users. Additionally, keep in mind that the code is for high-volume document conversion, where the requirements are a lot tougher than for desktop OCR libraries, so the releases are named more conservatively.
  • When we tested it, OCRopus performed better than all other open source OCR systems on standard datasets. It's probably the best open source OCR system you can get for English right now.
  • While Wikipedia is no crystal ball, the project plan is a kind of crystal ball and can be found at http://www.ocropus.org/ ; the beta release is expected Q1 2008, and the project is on schedule.

So, the project is working, and it's here to stay. People will probably want information on it, and it seems to me that it's something Wikipedia should cover. —Preceding unsigned comment added by Jcarnelian (talk • contribs) 08:44, 3 July 2007

The above discussion is preserved as an archive of the debate. Please do not modify it. Subsequent comments should be made on the appropriate discussion page (such as the article's talk page or in a deletion review). No further edits should be made to this page.