From 5cd1cd808367e5441b93effe35a29415813af8c0 Mon Sep 17 00:00:00 2001 From: Christian Wiese Date: Fri, 17 Aug 2012 15:19:25 +0200 Subject: [PATCH] tesseract-ocr: Added tesseract-ocr 3.01 - An OCR Engine originally developed at HP and now at Google --- graphic/tesseract-ocr/tesseract-ocr.conf | 16 ++++++++++ graphic/tesseract-ocr/tesseract-ocr.desc | 37 ++++++++++++++++++++++++ 2 files changed, 53 insertions(+) create mode 100644 graphic/tesseract-ocr/tesseract-ocr.conf create mode 100644 graphic/tesseract-ocr/tesseract-ocr.desc diff --git a/graphic/tesseract-ocr/tesseract-ocr.conf b/graphic/tesseract-ocr/tesseract-ocr.conf new file mode 100644 index 000000000..8f4089817 --- /dev/null +++ b/graphic/tesseract-ocr/tesseract-ocr.conf @@ -0,0 +1,16 @@ +# --- SDE-COPYRIGHT-NOTE-BEGIN --- +# This copyright note is auto-generated by ./scripts/Create-CopyPatch. +# +# Filename: package/.../tesseract-ocr/tesseract-ocr.conf +# Copyright (C) 2012 The OpenSDE Project +# +# More information can be found in the files COPYING and README. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; version 2 of the License. A copy of the +# GNU General Public License can be found in the file COPYING. +# --- SDE-COPYRIGHT-NOTE-END --- + +# we need to run autogen.sh to generate Makefile templates +autogen=1 diff --git a/graphic/tesseract-ocr/tesseract-ocr.desc b/graphic/tesseract-ocr/tesseract-ocr.desc new file mode 100644 index 000000000..23707dc3d --- /dev/null +++ b/graphic/tesseract-ocr/tesseract-ocr.desc @@ -0,0 +1,37 @@ +[COPY] --- SDE-COPYRIGHT-NOTE-BEGIN --- +[COPY] This copyright note is auto-generated by ./scripts/Create-CopyPatch. +[COPY] +[COPY] Filename: package/.../tesseract-ocr/tesseract-ocr.desc +[COPY] Copyright (C) 2012 The OpenSDE Project +[COPY] +[COPY] More information can be found in the files COPYING and README. +[COPY] +[COPY] This program is free software; you can redistribute it and/or modify +[COPY] it under the terms of the GNU General Public License as published by +[COPY] the Free Software Foundation; version 2 of the License. A copy of the +[COPY] GNU General Public License can be found in the file COPYING. +[COPY] --- SDE-COPYRIGHT-NOTE-END --- + +[I] An OCR Engine originally developed at HP and now at Google + +[T] The Tesseract OCR engine was one of the top 3 engines in the 1995 UNLV +[T] Accuracy test. Between 1995 and 2006 it had little work done on it, but +[T] since then it has been improved extensively by Google and is probably one +[T] of the most accurate open source OCR engines available. Combined with the +[T] Leptonica Image Processing Library it can read a wide variety of image +[T] formats and convert them to text in over 40 languages. + +[U] http://tesseract-ocr.googlecode.com/ + +[A] Google Inc. +[A] HP Labs (original version) +[M] Christian Wiese + +[C] extra/tool + +[L] APL +[S] Stable +[V] 3.01 +[P] X -----5---9 800.000 + +[D] 1207217170 tesseract-3.01.tar.gz http://tesseract-ocr.googlecode.com/files/