top-skimming import from sf.net

git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@2 d0cd1f9f-072b-0410-8dd7-cf729c803f20

trunk/.cvsignore

+BUILD
+OWNERS
+Makefile
+README.google
+runautoconf
+config_auto.h

trunk/AUTHORS

+Ray Smith (lead developer) <theraysmith@users.sourceforge.net>
+Phil Cheatle
+Simon Crouch
+Dan Johnson
+Mark Seaman
+Sheelagh Huddleston
+Chris Newton
+... and several others.

trunk/COPYING

+This package contains the Tesseract Open Source OCR Engine.
+Orignally developed at Hewlett Packard Laboratories Bristol and
+at Hewlett Packard Co, Greeley Colorado, all the code
+in this distribution is now licensed under the Apache License:
+
+** 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.
+
+
+Other Dependencies and Licenses:
+================================
+The Aspirin/MIGRAINES system is no longer used.
+
+Tesseract can also make use of the libtiff library. (www.libtiff.org)
+Without libtiff, Tesseract can only read uncompressed and G3 compressed
+TIFF files.

trunk/ChangeLog

+June  2006 - V1.0 of open source Tesseract checked-in.
+Sep 7 2006 - V1.01.
+          Added mfcpch.cpp and getopt.cpp for VC++.
+          Fixed problem with greyscale images and no libtiff.
+          Stopped debug window from being used for the usage output.
+          Fixed load of inttemp for big-endian architectures.
+          Fixed some Mac compilation issues.
+Oct 4 2006 - V1.02
+          Removed dependency on Aspirin.
+          Fixed a few missing Apache license headers.
+          Removed $log.
+Feb 2 2007 - V1.03
+          Added mftraining and cntraining.
+          Added baseapi with adaptive thresholding for grey and color.
+          Fixed many memory leaks.
+          Fixed several bugs including lack of use of adaptive classifier.
+          Added ifdefs to eliminate graphics code and add embedded platform support.
+          Incorporated several patches, including 64-bit builds, Mac builds.
+          Minor accuracy improvements.
+

trunk/INSTALL

+Copyright 1994, 1995, 1996, 1999, 2000, 2001, 2002 Free Software
+Foundation, Inc.
+
+   This file is free documentation; the Free Software Foundation gives
+unlimited permission to copy, distribute and modify it.
+
+Basic Installation
+==================
+
+   These are generic installation instructions.
+
+   The `configure' shell script attempts to guess correct values for
+various system-dependent variables used during compilation.  It uses
+those values to create a `Makefile' in each directory of the package.
+It may also create one or more `.h' files containing system-dependent
+definitions.  Finally, it creates a shell script `config.status' that
+you can run in the future to recreate the current configuration, and a
+file `config.log' containing compiler output (useful mainly for
+debugging `configure').
+
+   It can also use an optional file (typically called `config.cache'
+and enabled with `--cache-file=config.cache' or simply `-C') that saves
+the results of its tests to speed up reconfiguring.  (Caching is
+disabled by default to prevent problems with accidental use of stale
+cache files.)
+
+   If you need to do unusual things to compile the package, please try
+to figure out how `configure' could check whether to do them, and mail
+diffs or instructions to the address given in the `README' so they can
+be considered for the next release.  If you are using the cache, and at
+some point `config.cache' contains results you don't want to keep, you
+may remove or edit it.
+
+   The file `configure.ac' (or `configure.in') is used to create
+`configure' by a program called `autoconf'.  You only need
+`configure.ac' if you want to change it or regenerate `configure' using
+a newer version of `autoconf'.
+
+The simplest way to compile this package is:
+
+  1. `cd' to the directory containing the package's source code and type
+     `./configure' to configure the package for your system.  If you're
+     using `csh' on an old version of System V, you might need to type
+     `sh ./configure' instead to prevent `csh' from trying to execute
+     `configure' itself.
+
+     Running `configure' takes awhile.  While running, it prints some
+     messages telling which features it is checking for.
+
+  2. Type `make' to compile the package.
+
+  3. Optionally, type `make check' to run any self-tests that come with
+     the package.
+
+  4. Type `make install' to install the programs and any data files and
+     documentation.
+
+  5. You can remove the program binaries and object files from the
+     source code directory by typing `make clean'.  To also remove the
+     files that `configure' created (so you can compile the package for
+     a different kind of computer), type `make distclean'.  There is
+     also a `make maintainer-clean' target, but that is intended mainly
+     for the package's developers.  If you use it, you may have to get
+     all sorts of other programs in order to regenerate files that came
+     with the distribution.
+
+Compilers and Options
+=====================
+
+   Some systems require unusual options for compilation or linking that
+the `configure' script does not know about.  Run `./configure --help'
+for details on some of the pertinent environment variables.
+
+   You can give `configure' initial values for configuration parameters
+by setting variables in the command line or in the environment.  Here
+is an example:
+
+     ./configure CC=c89 CFLAGS=-O2 LIBS=-lposix
+
+   *Note Defining Variables::, for more details.
+
+Compiling For Multiple Architectures
+====================================
+
+   You can compile the package for more than one kind of computer at the
+same time, by placing the object files for each architecture in their
+own directory.  To do this, you must use a version of `make' that
+supports the `VPATH' variable, such as GNU `make'.  `cd' to the
+directory where you want the object files and executables to go and run
+the `configure' script.  `configure' automatically checks for the
+source code in the directory that `configure' is in and in `..'.
+
+   If you have to use a `make' that does not support the `VPATH'
+variable, you have to compile the package for one architecture at a
+time in the source code directory.  After you have installed the
+package for one architecture, use `make distclean' before reconfiguring
+for another architecture.
+
+Installation Names
+==================
+
+   By default, `make install' will install the package's files in
+`/usr/local/bin', `/usr/local/man', etc.  You can specify an
+installation prefix other than `/usr/local' by giving `configure' the
+option `--prefix=PATH'.
+
+   You can specify separate installation prefixes for
+architecture-specific files and architecture-independent files.  If you
+give `configure' the option `--exec-prefix=PATH', the package will use
+PATH as the prefix for installing programs and libraries.
+Documentation and other data files will still use the regular prefix.
+
+   In addition, if you use an unusual directory layout you can give
+options like `--bindir=PATH' to specify different values for particular
+kinds of files.  Run `configure --help' for a list of the directories
+you can set and what kinds of files go in them.
+
+   If the package supports it, you can cause programs to be installed
+with an extra prefix or suffix on their names by giving `configure' the
+option `--program-prefix=PREFIX' or `--program-suffix=SUFFIX'.
+
+Optional Features
+=================
+
+   Some packages pay attention to `--enable-FEATURE' options to
+`configure', where FEATURE indicates an optional part of the package.
+They may also pay attention to `--with-PACKAGE' options, where PACKAGE
+is something like `gnu-as' or `x' (for the X Window System).  The
+`README' should mention any `--enable-' and `--with-' options that the
+package recognizes.
+
+   For packages that use the X Window System, `configure' can usually
+find the X include and library files automatically, but if it doesn't,
+you can use the `configure' options `--x-includes=DIR' and
+`--x-libraries=DIR' to specify their locations.
+
+Specifying the System Type
+==========================
+
+   There may be some features `configure' cannot figure out
+automatically, but needs to determine by the type of machine the package
+will run on.  Usually, assuming the package is built to be run on the
+_same_ architectures, `configure' can figure that out, but if it prints
+a message saying it cannot guess the machine type, give it the
+`--build=TYPE' option.  TYPE can either be a short name for the system
+type, such as `sun4', or a canonical name which has the form:
+
+     CPU-COMPANY-SYSTEM
+
+where SYSTEM can have one of these forms:
+
+     OS KERNEL-OS
+
+   See the file `config.sub' for the possible values of each field.  If
+`config.sub' isn't included in this package, then this package doesn't
+need to know the machine type.
+
+   If you are _building_ compiler tools for cross-compiling, you should
+use the `--target=TYPE' option to select the type of system they will
+produce code for.
+
+   If you want to _use_ a cross compiler, that generates code for a
+platform different from the build platform, you should specify the
+"host" platform (i.e., that on which the generated programs will
+eventually be run) with `--host=TYPE'.
+
+Sharing Defaults
+================
+
+   If you want to set default values for `configure' scripts to share,
+you can create a site shell script called `config.site' that gives
+default values for variables like `CC', `cache_file', and `prefix'.
+`configure' looks for `PREFIX/share/config.site' if it exists, then
+`PREFIX/etc/config.site' if it exists.  Or, you can set the
+`CONFIG_SITE' environment variable to the location of the site script.
+A warning: not all `configure' scripts look for a site script.
+
+Defining Variables
+==================
+
+   Variables not defined in a site shell script can be set in the
+environment passed to `configure'.  However, some packages may run
+configure again during the build, and the customized values of these
+variables may be lost.  In order to avoid this problem, you should set
+them in the `configure' command line, using `VAR=value'.  For example:
+
+     ./configure CC=/usr/local2/bin/gcc
+
+will cause the specified gcc to be used as the C compiler (unless it is
+overridden in the site shell script).
+
+`configure' Invocation
+======================
+
+   `configure' recognizes the following options to control how it
+operates.
+
+`--help'
+`-h'
+     Print a summary of the options to `configure', and exit.
+
+`--version'
+`-V'
+     Print the version of Autoconf used to generate the `configure'
+     script, and exit.
+
+`--cache-file=FILE'
+     Enable the cache: use and save the results of the tests in FILE,
+     traditionally `config.cache'.  FILE defaults to `/dev/null' to
+     disable caching.
+
+`--config-cache'
+`-C'
+     Alias for `--cache-file=config.cache'.
+
+`--quiet'
+`--silent'
+`-q'
+     Do not print messages saying which checks are being made.  To
+     suppress all normal output, redirect it to `/dev/null' (any error
+     messages will still be shown).
+
+`--srcdir=DIR'
+     Look for the package's source code in directory DIR.  Usually
+     `configure' can determine that directory automatically.
+
+`configure' also accepts some other, not widely useful, options.  Run
+`configure --help' for more details.
+

trunk/Makefile.am

+# TODO(luc) Add 'doc' to this list when ready
+SUBDIRS = ccstruct ccutil classify cutil dict display image textord viewer wordrec ccmain training
+
+EXTRA_DIST = tessdata phototest.tif tesseract.dsp tesseract.dsw
+#EXTRA_DIST = doc/html doc/@PACKAGE_NAME@_@PACKAGE_VERSION@.pdf doc/@PACKAGE_NAME@_@PACKAGE_VERSION@.ps.gz
+
+dist-hook:
+# Need to remove CVS directories from directories
+# added using EXTRA_DIST. $(distdir)/tessdata would in
+# theory suffice.
+	rm -rf `find $(distdir) -name CVS`
+# Also remove extra files not needed in a distribution
+	rm -rf `find $(distdir) -name configure.ac`
+	rm -rf `find $(distdir) -name acinclude.m4`
+	rm -rf `find $(distdir) -name aclocal.m4`

trunk/NEWS

+Stub file. To be populated at a later stage.

trunk/README

+Introduction
+============
+This package contains the Tesseract Open Source OCR Engine.
+Orignally developed at Hewlett Packard Laboratories Bristol and
+at Hewlett Packard Co, Greeley Colorado, all the code
+in this distribution is now licensed under the Apache License:
+
+** 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.
+
+
+Other Dependencies and Licenses:
+================================
+The Aspirin/MIGRAINES system is no longer required.
+
+Tesseract can also make use of the libtiff library. (www.libtiff.org)
+Without libtiff, Tesseract can only read uncompressed and G3 compressed
+TIFF files.
+
+
+History:
+========
+The engine was developed at Hewlett Packard Laboratories Bristol and
+at Hewlett Packard Co, Greeley Colorado between 1985 and 1994, with some
+more changes made in 1996 to port to Windows, and some C++izing in 1998.
+A lot of the code was written in C, and then some more was written in C++.
+Since then all the code has been converted to at least compile with a C++
+compiler. Currently it builds under Linux with gcc2.95 and under Windows
+with VC++6. The C++ code makes heavy use of a list system using macros.
+This predates stl, was portable before stl, and is more efficent than stl
+lists, but has the big negative that if you do get a segmentation violation,
+it is hard to debug. Another "feature" of the C/C++ split is that the C++
+data structures get converted to C data structures to call the low-level C
+code. This is ugly, and the C++izing of the C code is a step towards
+eliminating the conversion, but it has not happened yet.
+
+
+Directory Structure (ordered by dependency):
+============================================
+ccmain     Top-level code. The main program resides in tesseractmain.cpp.
+display    An "editor" to view and operate on the internal structures.
+           (Requires a working viewer - batteries not included.)
+wordrec    The word-level recognizer.
+textord    The module that organizes(orders) text into lines and words.
+classify   The low-level character classifiers.
+ccstruct   Classes to hold information about a page as it is being processed.
+viewer     The client side of a client server viewing system.
+           Unfortunately, at this time, the server side is not available.
+image      Image class and processing functions.
+dict       Language model code.
+cutil      Code for file I/O, lists, heaps etc, from the old C code.
+ccutil     Somewhat newer code for lists, memory allocation etc from the
+           old C++ code.
+
+
+About the Engine
+================
+This code is a raw OCR engine. It has NO PAGE LAYOUT ANALYSIS, NO OUTPUT
+FORMATTING, and NO UI. It can only process an image of a single column
+and create text from it. It can detect fixed pitch vs proportional text.
+Having said that, in 1995, this engine was in the top 3 in terms of character
+accuracy, and it compiles and runs on both Linux and Windows. Another current
+limitation is that it only recognizes English and its character set is only
+US-ASCII. Training code IS included in the open source release however, and
+will be included in a future release.
+
+
+Using the Engine
+================
+The usage of both Windows and Linux versions is the same.
+The executable must reside in the same directory as the tessdata directory
+The command line is:
+tesseract <image.tif> <output> batch
+The image file requires an .tif extension for its type to be recognized
+correctly. If a file exists with the .tif extension replaced by .uzn, then it
+will be interpreted as a UNLV-style zone file. (See www.isri.unlv.edu for
+details of the zone files.)
+

trunk/ReleaseNotes

+Tesseract release notes Feb 2, 2007 - V1.03.
+Added mftraining and cntraining. Using an image with a box file, tesseract
+generates .tr output files. cntraining runs on the .tr files to make
+normproto that lives in tessdata. mftraining runs on the .tr files to
+make inttemp and pffmtable in tessdata. These are the main data files
+that tesseract uses to recognize characters. At present, the code to make
+dictionary files is not yet available, nor are any sample box files or
+rebuilt inttemp or documentation to create any of these. Recognition is
+still limited to the ASCII set, but when this problem is fixed, documentation
+will follow.
+
+Added a new API with adaptive thresholding for grey and color images.
+See ccmain/baseapi.h/cpp for details. The main program has been converted
+to use the API as an example. See main() in ccmain/tesseractmain.cpp for
+details. The API is designed to make it easy to add subclasses with ability
+to output the bounding boxes etc from the internal structures. The adaptive
+thresholding improves accuracy (most of the time) on non-binary images.
+
+Many memory leaks have been fixed. There are no known leaks left from using
+the API correctly.
+
+The adaptive classifier was not operating correctly. This bug, and several
+others have been fixed, including poor chopping, an indefinite (if not quite
+infinite) loop in the number parser, and a couple of crash bugs. Thanks to
+all that have contributed bugs and bug fixes.
+
+It is now possible to build without any of the graphics support to save code
+size using #define GRAPHICS_DISABLED. There is also a new EMBEDDED define
+for use on operating systems with limited library support.
+
+64-bit and Mac OSX buildability is now included in the mainline source tree.
+Thanks to all that have contributed patches and comments to help with that.
+1.03 is also endian-independent, apart from the tiff i/o, so if you use
+libtiff, the code should run on all platforms, even if you get/create new
+data files of a different endinanness.
+
+Some of the bug fixes improve accuracy, and so do some of the changes to
+DangAmbigs and user-words.
+
+Tesseract release notes, Oct 4 2006 - V1.02.
+Removed dependency on aspirin. *All* code is now licensed under Apache2.0.
+
+Tesseract release notes, Sep 7 2006 - V1.01.
+
+Fixes for this release:
+Added mfcpch.cpp and getopt.cpp for VC++.
+Fixed problem with greyscale images and no libtiff.
+Stopped debug window from being used for the usage output.
+Fixed load of inttemp for big-endian architectures.
+Fixed some Mac compilation issues.
+
+This version should read uncompressed 8 bit grey and 24 bit color tiffs
+without having to have libtiff. It does a dumb threshold though, so don't
+expect good results from poor contrast or images of natural scenes etc.
+
+If you just run tesseract with no command line args you should now get a
+sensible usage message on linux, with or without X-windows.
+
+If you can get it to compile on a PPC Mac, it may now run correctly,
+although not all the build issues are fixed yet.
+
+Building Tesseract:
+Windows:
+Unpack the tar.gz archive
+Open tesseract.dsw in DevStudio (preferably version 6, higher versions will be more difficult)
+Set Win32 - Release as the active configuration.
+Build.
+Copy tesseract.exe from bin.rel up one directory level.
+Run tesseract phototest.tif phototest
+This will create phototest.txt.
+
+Linux:
+Unpack the tar.gz archive
+./configure
+make
+Copy tesseract from ccmain up one directory level (or create a symbolic link)
+Run tesseract phototest.tif phototest
+This will create phototest.txt.

trunk/acinclude.m4

+# Master include for AC macros. This directory structure allows
+# for more flexibility with respect to CVS modules.
+#
+# Author: Luc Vincent
+
+### m4_include(config/ac_compile_check_sizeof.m4)dnl
+#m4_include(config/ac_create_stdint_h.m4)dnl
+#m4_include(config/ax_create_stdint_h.m4)dnl
+m4_include(config/ac_define_versionlevel.m4)dnl
+m4_include(config/acinclude_custom.m4)dnl

trunk/ccmain/Makefile.am

+SUBDIRS =
+AM_CPPFLAGS = \
+    -I$(top_srcdir)/ccutil -I$(top_srcdir)/ccstruct \
+    -I$(top_srcdir)/image -I$(top_srcdir)/viewer \
+    -I$(top_srcdir)/ccops -I$(top_srcdir)/dict \
+    -I$(top_srcdir)/classify -I$(top_srcdir)/display \
+    -I$(top_srcdir)/wordrec -I$(top_srcdir)/cutil \
+    -I$(top_srcdir)/textord
+
+EXTRA_DIST = \
+    adaptions.h applybox.h baseapi.h blobcmp.h \
+    callnet.h charcut.h \
+    control.h docqual.h expandblob.h fixspace.h fixxht.h \
+    imgscale.h matmatch.h output.h paircmp.h reject.h scaleimg.h \
+    tessbox.h tessedit.h tesseractmain.h tessvars.h tfacep.h \
+    tessembedded.h tfacepp.h tstruct.h werdit.h
+
+noinst_LIBRARIES = libtesseract_main.a
+libtesseract_main_a_SOURCES = \
+    tessedit.cpp adaptions.cpp applybox.cpp \
+    baseapi.cpp blobcmp.cpp \
+    callnet.cpp charcut.cpp charsample.cpp control.cpp \
+    docqual.cpp expandblob.cpp fixspace.cpp fixxht.cpp \
+    imgscale.cpp matmatch.cpp output.cpp paircmp.cpp \
+    reject.cpp scaleimg.cpp tessbox.cpp tessvars.cpp \
+    tfacepp.cpp tstruct.cpp werdit.cpp
+
+bin_PROGRAMS = tesseract
+tesseract_SOURCES = tesseractmain.cpp
+tesseract_LDADD = \
+    libtesseract_main.a \
+    ../display/libtesseract_display.a \
+    ../textord/libtesseract_textord.a \
+    ../wordrec/libtesseract_wordrec.a \
+    ../classify/libtesseract_classify.a \
+    ../dict/libtesseract_dict.a \
+    ../viewer/libtesseract_viewer.a \
+    ../image/libtesseract_image.a \
+    ../cutil/libtesseract_cutil.a \
+    ../ccstruct/libtesseract_ccstruct.a \
+    ../ccutil/libtesseract_ccutil.a

trunk/ccmain/adaptions.h

+/**********************************************************************
+ * File:        adaptions.h  (Formerly adaptions.h)
+ * Description: Functions used to adapt to blobs already confidently
+ *					identified
+ * Author:		Chris Newton
+ * Created:		Thu Oct  7 10:17:28 BST 1993
+ *
+ * (C) Copyright 1992, Hewlett-Packard Ltd.
+ ** 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           ADAPTIONS_H
+#define           ADAPTIONS_H
+
+#include          "charsample.h"
+#include          "charcut.h"
+#include          "notdll.h"
+
+extern BOOL_VAR_H (tessedit_reject_ems, FALSE, "Reject all m's");
+extern BOOL_VAR_H (tessedit_reject_suspect_ems, FALSE, "Reject suspect m's");
+extern double_VAR_H (tessedit_cluster_t1, 0.20,
+"t1 threshold for clustering samples");
+extern double_VAR_H (tessedit_cluster_t2, 0.40,
+"t2 threshold for clustering samples");
+extern double_VAR_H (tessedit_cluster_t3, 0.12,
+"Extra threshold for clustering samples, only keep a new sample if best score greater than this value");
+extern double_VAR_H (tessedit_cluster_accept_fraction, 0.80,
+"Largest fraction of characters in cluster for it to be used for adaption");
+extern INT_VAR_H (tessedit_cluster_min_size, 3,
+"Smallest number of samples in a cluster for it to be used for adaption");
+extern BOOL_VAR_H (tessedit_cluster_debug, FALSE,
+"Generate and print debug information for adaption by clustering");
+extern BOOL_VAR_H (tessedit_use_best_sample, FALSE,
+"Use best sample from cluster when adapting");
+extern BOOL_VAR_H (tessedit_test_cluster_input, FALSE,
+"Set reject map to enable cluster input to be measured");
+extern BOOL_VAR_H (tessedit_matrix_match, TRUE, "Use matrix matcher");
+extern BOOL_VAR_H (tessedit_old_matrix_match, FALSE, "Use matrix matcher");
+extern BOOL_VAR_H (tessedit_mm_use_non_adaption_set, FALSE,
+"Don't try to adapt to characters on this list");
+extern STRING_VAR_H (tessedit_non_adaption_set, ",.;:'~@*",
+"Characters to be avoided when adapting");
+extern BOOL_VAR_H (tessedit_mm_adapt_using_prototypes, TRUE,
+"Use prototypes when adapting");
+extern BOOL_VAR_H (tessedit_mm_use_prototypes, TRUE,
+"Use prototypes as clusters are built");
+extern BOOL_VAR_H (tessedit_mm_use_rejmap, FALSE,
+"Adapt to characters using reject map");
+extern BOOL_VAR_H (tessedit_mm_all_rejects, FALSE,
+"Adapt to all characters using, matrix matcher");
+extern BOOL_VAR_H (tessedit_mm_only_match_same_char, FALSE,
+"Only match samples against clusters for the same character");
+extern BOOL_VAR_H (tessedit_process_rns, FALSE, "Handle m - rn ambigs");
+extern BOOL_VAR_H (tessedit_demo_adaption, FALSE,
+"Display cut images and matrix match for demo purposes");
+extern INT_VAR_H (tessedit_demo_word1, 62,
+"Word number of first word to display");
+extern INT_VAR_H (tessedit_demo_word2, 64,
+"Word number of second word to display");
+extern STRING_VAR_H (tessedit_demo_file, "academe",
+"Name of document containing demo words");
+BOOL8 word_adaptable(  //should we adapt?
+                     WERD_RES *word,
+                     UINT16 mode);
+void collect_ems_for_adaption(WERD_RES *word,
+                              CHAR_SAMPLES_LIST *char_clusters,
+                              CHAR_SAMPLE_LIST *chars_waiting);
+void collect_characters_for_adaption(WERD_RES *word,
+                                     CHAR_SAMPLES_LIST *char_clusters,
+                                     CHAR_SAMPLE_LIST *chars_waiting);
+void cluster_sample(CHAR_SAMPLE *sample,
+                    CHAR_SAMPLES_LIST *char_clusters,
+                    CHAR_SAMPLE_LIST *chars_waiting);
+void check_wait_list(CHAR_SAMPLE_LIST *chars_waiting,
+                     CHAR_SAMPLE *sample,
+                     CHAR_SAMPLES *best_cluster);
+void complete_clustering(CHAR_SAMPLES_LIST *char_clusters,
+                         CHAR_SAMPLE_LIST *chars_waiting);
+void adapt_to_good_ems(WERD_RES *word,
+                       CHAR_SAMPLES_LIST *char_clusters,
+                       CHAR_SAMPLE_LIST *chars_waiting);
+void adapt_to_good_samples(WERD_RES *word,
+                           CHAR_SAMPLES_LIST *char_clusters,
+                           CHAR_SAMPLE_LIST *chars_waiting);
+void print_em_stats(CHAR_SAMPLES_LIST *char_clusters,
+                    CHAR_SAMPLE_LIST *chars_waiting);
+                                 //lines of the image
+CHAR_SAMPLE *clip_sample(PIXROW *pixrow,
+                         IMAGELINE *imlines,
+                         BOX pix_box,  //box of imlines extent
+                         BOOL8 white_on_black,
+                         char c);
+void display_cluster_prototypes(CHAR_SAMPLES_LIST *char_clusters); 
+void reject_all_ems(WERD_RES *word); 
+void reject_all_fullstops(WERD_RES *word); 
+void reject_suspect_ems(WERD_RES *word); 
+void reject_suspect_fullstops(WERD_RES *word); 
+BOOL8 suspect_em(WERD_RES *word, INT16 index); 
+BOOL8 suspect_fullstop(WERD_RES *word, INT16 i); 
+#endif

trunk/ccmain/applybox.h

+/**********************************************************************
+ * File:        applybox.h  (Formerly applybox.h)
+ * Description: Re segment rows according to box file data
+ * Author:		Phil Cheatle
+ * Created:		Wed Nov 24 09:11:23 GMT 1993
+ *
+ * (C) Copyright 1993, Hewlett-Packard Ltd.
+ ** 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           APPLYBOX_H
+#define           APPLYBOX_H
+
+#include          "varable.h"
+#include          "ocrblock.h"
+#include          "ocrrow.h"
+#include          "notdll.h"
+
+extern BOOL_VAR_H (applybox_rebalance, TRUE, "Drop dead");
+extern INT_VAR_H (applybox_debug, 0, "Debug level");
+extern STRING_VAR_H (applybox_test_exclusions, "|",
+"Chars ignored for testing");
+extern double_VAR_H (applybox_error_band, 0.15, "Err band as fract of xht");
+void apply_boxes(BLOCK_LIST *block_list    //real blocks
+                );
+void clear_any_old_text(                        //remove correct text
+                        BLOCK_LIST *block_list  //real blocks
+                       );
+BOOL8 read_next_box(FILE* box_file,  //
+                    BOX *box,
+                    char *ch);
+ROW *find_row_of_box(                         //
+                     BLOCK_LIST *block_list,  //real blocks
+                     BOX box,                 //from boxfile
+                     INT16 &block_id,
+                     INT16 &row_id_to_process);
+INT16 resegment_box(  //
+                    ROW *row,
+                    BOX box,
+                    char *ch,
+                    INT16 block_id,
+                    INT16 row_id,
+                    INT16 boxfile_lineno,
+                    INT16 boxfile_charno);
+void tidy_up(                         //
+             BLOCK_LIST *block_list,  //real blocks
+             INT16 &ok_char_count,
+             INT16 &ok_row_count,
+             INT16 &unlabelled_words,
+             INT16 *tgt_char_counts,
+             INT16 &rebalance_count,
+             char &min_char,
+             INT16 &min_samples,
+             INT16 &final_labelled_blob_count);
+void report_failed_box(INT16 boxfile_lineno,
+                       INT16 boxfile_charno,
+                       BOX box,
+                       char *box_ch,
+                       const char *err_msg);
+void apply_box_training(BLOCK_LIST *block_list);
+void apply_box_testing(BLOCK_LIST *block_list);
+#endif

trunk/ccmain/baseapi.h

+///////////////////////////////////////////////////////////////////////
+// File:        baseapi.h
+// Description: Simple API for calling tesseract.
+// Author:      Ray Smith
+// Created:     Fri Oct 06 15:35:01 PDT 2006
+//
+// (C) Copyright 2006, 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 THIRD_PARTY_TESSERACT_CCMAIN_BASEAPI_H__
+#define THIRD_PARTY_TESSERACT_CCMAIN_BASEAPI_H__
+
+#include <string>
+
+#include "host.h"
+#include "ocrclass.h"
+
+class PAGE_RES;
+class BLOCK_LIST;
+
+// Base class for all tesseract APIs.
+// Specific classes can add ability to work on different inputs or produce
+// different outputs.
+
+class TessBaseAPI {
+ public:
+  // Start tesseract.
+  // The datapath must be the name of the data directory or some other file
+  // in which the data directory resides (for instance argv[0].)
+  // The configfile is the name of a file in the tessconfigs directory
+  // (eg batch) or NULL to run on defaults.
+  // Outputbase may also be NULL, and is the basename of various output files.
+  // If the output of any of these files is enabled, then a name must be given.
+  // If numeric_mode is true, only possible digits and roman numbers are
+  // returned. Returns 0 if successful. Crashes if not.
+  // The argc and argv may be 0 and NULL respectively. They are used for
+  // providing config files for debug/display purposes.
+  // TODO(rays) get the facts straight. Is it OK to call
+  // it more than once? Make it properly check for errors and return them.
+  static int Init(const char* datapath, const char* outputbase,
+                  const char* configfile, bool numeric_mode,
+                  int argc, char* argv[]);
+
+  // Recognize a rectangle from an image and return the result as a string.
+  // May be called many times for a single Init.
+  // Currently has no error checking.
+  // Greyscale of 8 and color of 24 or 32 bits per pixel may be given.
+  // Palette color images will not work properly and must be converted to
+  // 24 bit.
+  // Binary images of 1 bit per pixel may also be given but they must be
+  // byte packed with the MSB of the first byte being the first pixel, and a
+  // 1 represents WHITE. For binary images set bytes_per_pixel=0.
+  // The recognized text is returned as a char* which (in future will be coded
+  // as UTF8 and) must be freed with the delete [] operator.
+  static char* TesseractRect(const UINT8* imagedata,
+                             int bytes_per_pixel,
+                             int bytes_per_line,
+                             int left, int top, int width, int height);
+
+  // Call between pages or documents etc to free up memory and forget
+  // adaptive data.
+  static void ClearAdaptiveClassifier();
+
+  // Close down tesseract and free up memory.
+  static void End();
+
+  // Dump the internal binary image to a PGM file.
+  static void DumpPGM(const char* filename);
+
+ protected:
+  // Copy the given image rectangle to Tesseract, with adaptive thresholding
+  // if the image is not already binary.
+  static void CopyImageToTesseract(const UINT8* imagedata,
+                                   int bytes_per_pixel,
+                                   int bytes_per_line,
+                                   int left, int top, int width, int height);
+
+  // Compute the Otsu threshold(s) for the given image rectangle, making one
+  // for each channel. Each channel is always one byte per pixel.
+  // Returns an array of threshold values and an array of hi_values, such
+  // that a pixel value >threshold[channel] is considered foreground if
+  // hi_values[channel] is 0 or background if 1. A hi_value of -1 indicates
+  // that there is no apparent foreground. At least one hi_value will not be -1.
+  // thresholds and hi_values are assumed to be of bytes_per_pixel size.
+  static void OtsuThreshold(const UINT8* imagedata,
+                           int bytes_per_pixel,
+                           int bytes_per_line,
+                           int left, int top, int right, int bottom,
+                           int* thresholds,
+                           int* hi_values);
+
+  // Compute the histogram for the given image rectangle, and the given
+  // channel. (Channel pointed to by imagedata.) Each channel is always
+  // one byte per pixel.
+  // Bytes per pixel is used to skip channels not being
+  // counted with this call in a multi-channel (pixel-major) image.
+  // Histogram is always a 256 element array to count occurrences of
+  // each pixel value.
+  static void HistogramRect(const UINT8* imagedata,
+                            int bytes_per_pixel,
+                            int bytes_per_line,
+                            int left, int top, int right, int bottom,
+                            int* histogram);
+
+  // Compute the Otsu threshold(s) for the given histogram.
+  // Also returns H = total count in histogram, and
+  // omega0 = count of histogram below threshold.
+  static int OtsuStats(const int* histogram,
+                       int* H_out,
+                       int* omega0_out);
+
+  // Threshold the given grey or color image into the tesseract global
+  // image ready for recognition. Requires thresholds and hi_value
+  // produced by OtsuThreshold above.
+  static void ThresholdRect(const UINT8* imagedata,
+                            int bytes_per_pixel,
+                            int bytes_per_line,
+                            int left, int top,
+                            int width, int height,
+                            const int* thresholds,
+                            const int* hi_values);
+
+  // Cut out the requested rectangle of the binary image to the
+  // tesseract global image ready for recognition.
+  static void CopyBinaryRect(const UINT8* imagedata,
+                             int bytes_per_line,
+                             int left, int top,
+                             int width, int height);
+
+  // Low-level function to recognize the current global image to a string.
+  static char* RecognizeToString();
+
+  // Find lines from the image making the BLOCK_LIST.
+  static void FindLines(BLOCK_LIST* block_list);
+
+  // Recognize the tesseract global image and return the result as Tesseract
+  // internal structures.
+  static PAGE_RES* Recognize(BLOCK_LIST* block_list, ETEXT_DESC* monitor);
+
+  // Convert (and free) the internal data structures into a text string.
+  static char* TesseractToText(PAGE_RES* page_res);
+};
+
+#endif  // THIRD_PARTY_TESSERACT_CCMAIN_BASEAPI_H__

trunk/ccmain/blobcmp.h

+/**********************************************************************
+ * File:			blobcmp.c
+ * Description: Code to compare blobs using the adaptive matcher.
+ * Author:		Ray Smith
+ * Created:		Wed Apr 21 09:28:51 BST 1993
+ *
+ * (C) Copyright 1993, Hewlett-Packard Ltd.
+ ** 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           BLOBCMP_H
+#define           BLOBCMP_H
+
+#include          "tstruct.h"
+
+float compare_tess_blobs(TBLOB *blob1,
+                         TEXTROW *row1,
+                         TBLOB *blob2,
+                         TEXTROW *row2);
+#endif