3.01 code from http://github.com/jimregan/tesseract-ocr with addaptio…

…ns related to Linux and Windows (VC2008) compile process git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@526 d0cd1f9f-072b-0410-8dd7-cf729c803f20
NinnOgTonic · Nov 23, 2010 · 4523ce9 · 4523ce9
1 parent 7511d76
commit 4523ce9
Show file tree

Hide file tree

Showing 558 changed files with 51,651 additions and 41,572 deletions.
diff --git a/ChangeLog b/ChangeLog
@@ -1,3 +1,38 @@
+2010-09-22 - V3.01
+  * Thread-safety! Moved all critical globals and statics to
+    members of the appropriate class. Tesseract is now
+    thread-safe (multiple instances can be used in parallel
+    in multiple threads.) with the minor exception that some
+    control parameters are still global and affect all threads.
+  * Added Cube, a new recognizer for Arabic. Cube can also be
+    used in combination with normal Tesseract for other languages
+    with an improvement in accuracy at the cost of (much) lower speed.
+    There is no training module for Cube yet.
+  * OcrEngineMode in Init replaces AccuracyVSpeed to control cube.
+  * Greatly improved segmentation search with consequent accuracy and
+    speed improvements, especially for Chinese.
+  * Added PageIterator and ResultIterator as cleaner ways to get the
+    full results out of Tesseract, that are not currently provided
+    by any of the TessBaseAPI::Get* methods.
+    All other methods, such as the ETEXT_STRUCT in particular are
+    deprecated and will be deleted in the future.
+  * ApplyBoxes totally rewritten to make training easier.
+    It can now cope with touching/overlapping training characters,
+    and a new boxfile format allows word boxes instead of character
+    boxes, BUT to use that you have to have already boostrapped the
+    language with character boxes. "Cyclic dependency" on traineddata.
+  * Auto orientation and script detection added to page layout analysis.
+  * Deleted *lots* of dead code.
+  * Fixxht module replaced with scalable data-driven module.
+  * Output font characteristics accuracy improved.
+  * Removed the double conversion at each classification.
+  * Upgraded oldest structs to be classes and deprecated PBLOB.
+  * Removed non-deterministic baseline fit.
+  * Added fixed length dawgs for Chinese.
+  * Handling of vertical text improved.
+  * Handling of leader dots improved.
+  * Table detection greatly improved.
+
 2010-09-21 - V3.00
   * Preparations for thread safety:
      * Changed TessBaseAPI methods to be non-static

diff --git a/Makefile.am b/Makefile.am
@@ -1,6 +1,6 @@
 # TODO(luc) Add 'doc' to this list when ready
 ACLOCAL_AMFLAGS = -I m4
-SUBDIRS = ccstruct ccutil classify cutil dict image textord viewer wordrec ccmain training tessdata testing java api vs2008
+SUBDIRS = ccstruct ccutil classify cube cutil dict image neural_networks/runtime textord viewer wordrec ccmain training tessdata testing java api
 #if USING_GETTEXT
 #SUBDIRS += po
 #AM_CPPFLAGS = -DLOCALEDIR=\"$(localedir)\"

diff --git a/Makefile.in b/Makefile.in
@@ -234,7 +234,7 @@ top_srcdir = @top_srcdir@
 
 # TODO(luc) Add 'doc' to this list when ready
 ACLOCAL_AMFLAGS = -I m4
-SUBDIRS = ccstruct ccutil classify cutil dict image textord viewer wordrec ccmain training tessdata testing java api vs2008
+SUBDIRS = ccstruct ccutil classify cube cutil dict image neural_networks/runtime textord viewer wordrec ccmain training tessdata testing java api
 #if USING_GETTEXT
 #SUBDIRS += po
 #AM_CPPFLAGS = -DLOCALEDIR=\"$(localedir)\"

diff --git a/ReleaseNotes b/ReleaseNotes
@@ -1,3 +1,38 @@
+Tesseract release notes Oct 1 2010 - V3.01
+  * Thread-safety! Moved all critical globals and statics to
+    members of the appropriate class. Tesseract is now
+    thread-safe (multiple instances can be used in parallel
+    in multiple threads.) with the minor exception that some
+    control parameters are still global and affect all threads.
+  * Added Cube, a new recognizer for Arabic. Cube can also be
+    used in combination with normal Tesseract for other languages
+    with an improvement in accuracy at the cost of (much) lower speed.
+    There is no training module for Cube yet.
+  * OcrEngineMode in Init replaces AccuracyVSpeed to control cube.
+  * Greatly improved segmentation search with consequent accuracy and
+    speed improvements, especially for Chinese.
+  * Added PageIterator and ResultIterator as cleaner ways to get the
+    full results out of Tesseract, that are not currently provided
+    by any of the TessBaseAPI::Get* methods.
+    All other methods, such as the ETEXT_STRUCT in particular are
+    deprecated and will be deleted in the future.
+  * ApplyBoxes totally rewritten to make training easier.
+    It can now cope with touching/overlapping training characters,
+    and a new boxfile format allows word boxes instead of character
+    boxes, BUT to use that you have to have already boostrapped the
+    language with character boxes. "Cyclic dependency" on traineddata.
+  * Auto orientation and script detection added to page layout analysis.
+  * Deleted *lots* of dead code.
+  * Fixxht module replaced with scalable data-driven module.
+  * Output font characteristics accuracy improved.
+  * Removed the double conversion at each classification.
+  * Upgraded oldest structs to be classes and deprecated PBLOB.
+  * Removed non-deterministic baseline fit.
+  * Added fixed length dawgs for Chinese.
+  * Handling of vertical text improved.
+  * Handling of leader dots improved.
+  * Table detection greatly improved.
+
 Tesseract release notes Sep 30 2010 - V3.00
   * Preparations for thread safety:
      * Changed TessBaseAPI methods to be non-static

diff --git a/api/Makefile.am b/api/Makefile.am
@@ -8,13 +8,15 @@ AM_CPPFLAGS = -DLOCALEDIR=\"$(localedir)\"\
     -I$(top_srcdir)/textord 
 
 include_HEADERS = \
-    baseapi.h tesseractmain.h
+    apitypes.h baseapi.h pageiterator.h resultiterator.h tesseractmain.h
 
 lib_LTLIBRARIES = libtesseract_api.la
-libtesseract_api_la_SOURCES = baseapi.cpp
+libtesseract_api_la_SOURCES = baseapi.cpp pageiterator.cpp resultiterator.cpp
 libtesseract_api_la_LDFLAGS = -version-info $(GENERIC_LIBRARY_VERSION)
 libtesseract_api_la_LIBADD = \
     ../ccmain/libtesseract_main.la \
+    ../cube/libtesseract_cube.la \
+    ../neural_networks/runtime/libtesseract_neural.la \
     ../textord/libtesseract_textord.la \
     ../wordrec/libtesseract_wordrec.la \
     ../classify/libtesseract_classify.la \

diff --git a/api/Makefile.in b/api/Makefile.in
@@ -74,6 +74,8 @@ am__installdirs = "$(DESTDIR)$(libdir)" "$(DESTDIR)$(bindir)" \
 	"$(DESTDIR)$(includedir)"
 LTLIBRARIES = $(lib_LTLIBRARIES)
 libtesseract_api_la_DEPENDENCIES = ../ccmain/libtesseract_main.la \
+	../cube/libtesseract_cube.la \
+	../neural_networks/runtime/libtesseract_neural.la \
 	../textord/libtesseract_textord.la \
 	../wordrec/libtesseract_wordrec.la \
 	../classify/libtesseract_classify.la \
@@ -82,7 +84,8 @@ libtesseract_api_la_DEPENDENCIES = ../ccmain/libtesseract_main.la \
 	../image/libtesseract_image.la ../cutil/libtesseract_cutil.la \
 	../viewer/libtesseract_viewer.la \
 	../ccutil/libtesseract_ccutil.la
-am_libtesseract_api_la_OBJECTS = baseapi.lo
+am_libtesseract_api_la_OBJECTS = baseapi.lo pageiterator.lo \
+	resultiterator.lo
 libtesseract_api_la_OBJECTS = $(am_libtesseract_api_la_OBJECTS)
 libtesseract_api_la_LINK = $(LIBTOOL) --tag=CXX $(AM_LIBTOOLFLAGS) \
 	$(LIBTOOLFLAGS) --mode=link $(CXXLD) $(AM_CXXFLAGS) \
@@ -294,13 +297,15 @@ AM_CPPFLAGS = -DLOCALEDIR=\"$(localedir)\"\
     -I$(top_srcdir)/textord 
 
 include_HEADERS = \
-    baseapi.h tesseractmain.h
+    apitypes.h baseapi.h pageiterator.h resultiterator.h tesseractmain.h
 
 lib_LTLIBRARIES = libtesseract_api.la
-libtesseract_api_la_SOURCES = baseapi.cpp
+libtesseract_api_la_SOURCES = baseapi.cpp pageiterator.cpp resultiterator.cpp
 libtesseract_api_la_LDFLAGS = -version-info $(GENERIC_LIBRARY_VERSION)
 libtesseract_api_la_LIBADD = \
     ../ccmain/libtesseract_main.la \
+    ../cube/libtesseract_cube.la \
+    ../neural_networks/runtime/libtesseract_neural.la \
     ../textord/libtesseract_textord.la \
     ../wordrec/libtesseract_wordrec.la \
     ../classify/libtesseract_classify.la \
@@ -446,6 +451,8 @@ distclean-compile:
 	-rm -f *.tab.c
 
 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/baseapi.Plo@am__quote@
+@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/pageiterator.Plo@am__quote@
+@AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/resultiterator.Plo@am__quote@
 @AMDEP_TRUE@@am__include@ @am__quote@./$(DEPDIR)/tesseractmain.Po@am__quote@
 
 .cpp.o:

diff --git a/api/apitypes.h b/api/apitypes.h
@@ -0,0 +1,31 @@
+///////////////////////////////////////////////////////////////////////
+// File:        apitypes.h
+// Description: Types used in both the API and internally
+// Author:      Ray Smith
+// Created:     Wed Mar 03 09:22:53 PST 2010
+//
+// (C) Copyright 2010, Google Inc.
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+// http://www.apache.org/licenses/LICENSE-2.0
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+//
+///////////////////////////////////////////////////////////////////////
+
+#ifndef TESSERACT_API_APITYPES_H__
+#define TESSERACT_API_APITYPES_H__
+
+#include "publictypes.h"
+
+// The types used by the API and Page/ResultIterator can be found in
+// ccstruct/publictypes.h.
+// API interfaces and API users should be sure to include this file, rather
+// than the lower-level one, and lower-level code should be sure to include
+// only the lower-level file.
+
+#endif  // TESSERACT_API_APITYPES_H__