Projects / WeOCR


WeOCR is a platform for Web-enabled OCR (Optical Character Reader/Recognition) systems. It enables people to use character recognition over networks. A WeOCR server receives document images from users, recognizes text in the images, and returns recognition results to the users. WeOCR does not have its own character recognition engine. Instead, it is intended to accommodate various existing character recognition engines.

Operating Systems

Recent releases

  •  15 Jun 2012 13:52

    Release Notes: Multi-character recognition mode has been added. JPEG handling has been fixed.

    •  25 Apr 2009 17:11

      Release Notes: The license has been changed to Apache 2.0. Automake has been introduced. Some code and document refinements have been made.

      •  19 Aug 2008 15:35

        Release Notes: A simple input buffer (queue) has been added so that the server can handle more requests at once.

        •  12 May 2007 18:05

          Release Notes: A minor fix has been made for showing tag-like text properly. The source code of bin_disc has been released.

          •  26 Jun 2006 14:09

            Release Notes: A file download feature has been added. Multiple data can be presented by this feature. Presentation of the recognition result in raw text format is now supported. Some minor code fixes were made.


            Project Spotlight


            A Fluent OpenStack client API for Java.


            Project Spotlight

            TurnKey TWiki Appliance

            A TWiki appliance that is easy to use and lightweight.