March 2011 - Olena-patches

last-svn-commit-765-gd3a06bf Add Base64 conversion routines.
by Guillaume Lazzara 28 Mar '11

28 Mar '11

* scribo/scribo/convert/from_base64.hh, * scribo/scribo/convert/to_base64.hh: New routines. * scribo/tests/Makefile.am, * scribo/tests/convert/Makefile.am, * scribo/tests/convert/base64.cc: New associated test. --- scribo/ChangeLog | 11 ++ scribo/scribo/convert/from_base64.hh | 217 ++++++++++++++++++++++++++++ scribo/scribo/convert/to_base64.hh | 185 ++++++++++++++++++++++++ scribo/tests/Makefile.am | 1 + scribo/tests/{core => convert}/Makefile.am | 8 +- scribo/tests/convert/base64.cc | 89 ++++++++++++ 6 files changed, 507 insertions(+), 4 deletions(-) create mode 100644 scribo/scribo/convert/from_base64.hh create mode 100644 scribo/scribo/convert/to_base64.hh copy scribo/tests/{core => convert}/Makefile.am (84%) create mode 100644 scribo/tests/convert/base64.cc diff --git a/scribo/ChangeLog b/scribo/ChangeLog index ef97bf9..9cbfca1 100644 --- a/scribo/ChangeLog +++ b/scribo/ChangeLog @@ -1,3 +1,14 @@ +2011-02-17 Guillaume Lazzara <z(a)lrde.epita.fr> + + Add Base64 conversion routines. + + * scribo/scribo/convert/from_base64.hh, + * scribo/scribo/convert/to_base64.hh: New routines. + + * scribo/tests/Makefile.am, + * scribo/tests/convert/Makefile.am, + * scribo/tests/convert/base64.cc: New associated test. + 2011-02-05 Guillaume Lazzara <z(a)lrde.epita.fr> Add support for whitespace separators visualization. diff --git a/scribo/scribo/convert/from_base64.hh b/scribo/scribo/convert/from_base64.hh new file mode 100644 index 0000000..8c14a0f --- /dev/null +++ b/scribo/scribo/convert/from_base64.hh @@ -0,0 +1,217 @@ +// Copyright (C) 2011 EPITA Research and Development Laboratory (LRDE) +// +// This file is part of Olena. +// +// Olena 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. +// +// Olena is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +// General Public License for more details. +// +// You should have received a copy of the GNU General Public License +// along with Olena. If not, see <http://www.gnu.org/licenses/>. +// +// As a special exception, you may use this file as part of a free +// software project without restriction. Specifically, if other files +// instantiate templates or use macros or inline functions from this +// file, or you compile this file and link it with other files to produce +// an executable, this file does not by itself cause the resulting +// executable to be covered by the GNU General Public License. This +// exception does not however invalidate any other reasons why the +// executable file might be covered by the GNU General Public License. + + + +#ifndef SCRIBO_CONVERT_FROM_BASE64_HH +# define SCRIBO_CONVERT_FROM_BASE64_HH + +/*! \file + + \brief Decode base64 raw data and convert it to an image. + + Based on Bob Trower's code. + http://base64.sourceforge.net/b64.c + + LICENCE: Copyright (c) 2001 Bob Trower, Trantor Standard Systems Inc. + + Permission is hereby granted, free of charge, to any person + obtaining a copy of this software and associated + documentation files (the "Software"), to deal in the + Software without restriction, including without limitation + the rights to use, copy, modify, merge, publish, distribute, + sublicense, and/or sell copies of the Software, and to + permit persons to whom the Software is furnished to do so, + subject to the following conditions: + + The above copyright notice and this permission notice shall + be included in all copies or substantial portions of the + Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY + KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE + WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR + PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS + OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR + OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE + SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +#include <cstdio> +#include <cstdlib> + +# include <mln/border/resize.hh> +# include <mln/core/image/image2d.hh> +# include <mln/util/array.hh> + + + +namespace scribo +{ + + namespace convert + { + + using namespace mln; + + template <typename I> + void from_base64(const util::array<unsigned char>& data64, + Image& output); + + +# if defined HAVE_QT + + template <typename I> + void from_base64(const QString& data64, Image& output_); + +# endif // ! HAVE_QT + + +# ifndef MLN_INCLUDE_ONLY + + + namespace internal + { + + /* + ** Translation Table to decode + */ + static const char cd64[]="|$$$}rstuvwxyz{$$$$$$$>?@ABCDEFGHIJKLMNOPQRSTUVW$$$$$$XYZ[\\]^_`abcdefghijklmnopq"; + + /* + ** decodeblock + ** + ** decode 4 '6-bit' characters into 3 8-bit binary bytes + */ + inline + void + decodeblock(unsigned char in[4], unsigned char out[3]) + { + out[ 0 ] = (unsigned char) (in[0] << 2 | in[1] >> 4); + out[ 1 ] = (unsigned char) (in[1] << 4 | in[2] >> 2); + out[ 2 ] = (unsigned char) (((in[2] << 6) & 0xc0) | in[3]); + } + + + template <typename V, typename I> + void + from_base64_(const V& data64, const unsigned length, Image& output_) + { + trace::entering("scribo::convert::from_base64_"); + + mln_precondition(exact(output_).is_valid()); + using namespace internal; + + I& output = exact(output_); + + unsigned char in[4], out[3], v; + int i, len; + + border::resize(output, 0); // Make sure there is no border! + + unsigned char *ptr = (unsigned char *)output.buffer(); + unsigned char *end_ptr = (unsigned char *)(output.buffer() + output.nelements()); + + for (unsigned idx = 0; idx < length;) + { + for(len = 0, i = 0; i < 4 && idx < length; i++) + { + v = 0; + while(idx < length && v == 0) + { + v = (unsigned char) data64[idx++]; + v = (unsigned char) ((v < 43 || v > 122) ? 0 : cd64[ v - 43 ]); + if(v) + { + v = (unsigned char) ((v == '$') ? 0 : v - 61); + } + } + if(idx < length) + { + len++; + if(v) + { + in[ i ] = (unsigned char) (v - 1); + } + } + else + { + in[i] = 0; + } + } + if(len) + { + decodeblock(in, out); + for(i = 0; i < len - 1 && ptr != end_ptr; i++) + { + *ptr++ = out[i]; + } + } + } + + trace::exiting("scribo::convert::to_base64_"); + } + + + } // end of namespace scribo::convert::internal + + + template <typename I> + void + from_base64(const util::array<unsigned char>& data64, Image& output_) + { + trace::entering("scribo::convert::from_base64"); + + internal::from_base64_(data64, data64.nelements(), output_); + + trace::exiting("scribo::convert::to_base64"); + } + + +# if defined HAVE_QT + + template <typename I> + void + from_base64(const QString& data64, Image& output_) + { + trace::entering("scribo::convert::from_base64"); + + QByteArray data64_ = data64.toAscii(); + internal::from_base64_(data64_.constData(), data64_.size(), output_); + + trace::exiting("scribo::convert::to_base64"); + } + +# endif // ! HAVE_QT + + +# endif // ! MLN_INCLUDE_ONLY + + } // end of namespace scribo::convert + +} // end of namespace scribo + +#endif // ! SCRIBO_CONVERT_FROM_BASE64_HH diff --git a/scribo/scribo/convert/to_base64.hh b/scribo/scribo/convert/to_base64.hh new file mode 100644 index 0000000..8df3ed2 --- /dev/null +++ b/scribo/scribo/convert/to_base64.hh @@ -0,0 +1,185 @@ +// Copyright (C) 2011 EPITA Research and Development Laboratory (LRDE) +// +// This file is part of Olena. +// +// Olena 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. +// +// Olena is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +// General Public License for more details. +// +// You should have received a copy of the GNU General Public License +// along with Olena. If not, see <http://www.gnu.org/licenses/>. +// +// As a special exception, you may use this file as part of a free +// software project without restriction. Specifically, if other files +// instantiate templates or use macros or inline functions from this +// file, or you compile this file and link it with other files to produce +// an executable, this file does not by itself cause the resulting +// executable to be covered by the GNU General Public License. This +// exception does not however invalidate any other reasons why the +// executable file might be covered by the GNU General Public License. + + + +#ifndef SCRIBO_CONVERT_TO_BASE64_HH +# define SCRIBO_CONVERT_TO_BASE64_HH + +/*! \file + + \brief Encode an image into base64 raw data. + + Based on Bob Trower's code. + http://base64.sourceforge.net/b64.c + + LICENCE: Copyright (c) 2001 Bob Trower, Trantor Standard Systems Inc. + + Permission is hereby granted, free of charge, to any person + obtaining a copy of this software and associated + documentation files (the "Software"), to deal in the + Software without restriction, including without limitation + the rights to use, copy, modify, merge, publish, distribute, + sublicense, and/or sell copies of the Software, and to + permit persons to whom the Software is furnished to do so, + subject to the following conditions: + + The above copyright notice and this permission notice shall + be included in all copies or substantial portions of the + Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY + KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE + WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR + PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS + OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR + OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE + SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. +*/ + +# include <cstdio> +# include <cstdlib> + +# include <mln/border/resize.hh> +# include <mln/core/image/image2d.hh> +# include <mln/util/array.hh> + + +# define B64_DEF_LINE_SIZE 72 + +namespace scribo +{ + + namespace convert + { + + using namespace mln; + + + template <typename I> + void + to_base64(const Image& input, util::array<unsigned char>& output); + + +# ifndef MLN_INCLUDE_ONLY + + + namespace internal + { + + /* + ** Translation Table as described in RFC1113 + */ + static const char cb64[]="ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"; + + /* + ** encodeblock + ** + ** encode 3 8-bit binary bytes as 4 '6-bit' characters + */ + inline + void + encodeblock(unsigned char in[3], unsigned char out[4], int len) + { + out[0] = cb64[ in[0] >> 2 ]; + out[1] = cb64[ ((in[0] & 0x03) << 4) | ((in[1] & 0xf0) >> 4) ]; + out[2] = (unsigned char) (len > 1 ? cb64[ ((in[1] & 0x0f) << 2) | ((in[2] & 0xc0) >> 6) ] : '='); + out[3] = (unsigned char) (len > 2 ? cb64[ in[2] & 0x3f ] : '='); + } + + } // end of namespace scribo::convert::internal + + + + template <typename I> + void + to_base64(const Image& input_, util::array<unsigned char>& output) + { + trace::entering("scribo::convert::to_base64"); + + mln_precondition(exact(input_).is_valid()); + using namespace internal; + + const I& input = exact(input_); + + unsigned char in[3], out[4]; + int i, len, blocksout = 0; + + // FIXME: Take border into account while moving pointer and + // remove that call. + border::resize(input, 0); + + const unsigned char + *end_ptr = (unsigned char *) (input.buffer() + input.nelements()), + *ptr = (unsigned char *)input.buffer(); + + while(ptr != end_ptr) + { + len = 0; + for(i = 0; i < 3; ++i) + { + if (ptr != end_ptr) + { + in[i] = (unsigned char) *ptr++; + ++len; + } + else + { + in[i] = 0; + for(++i; i < 3; ++i) + in[i] = 0; + } + } + if(len) + { + encodeblock(in, out, len); + for(i = 0; i < 4; ++i) + output.append(out[i]); + ++blocksout; + } + if(blocksout >= (B64_DEF_LINE_SIZE/4) || ptr == end_ptr) + { + if(blocksout) + { + output.append('\r'); + output.append('\n'); + } + blocksout = 0; + } + } + + trace::exiting("scribo::convert::to_base64"); + } + +# endif // ! MLN_INCLUDE_ONLY + +# undef B64_DEF_LINE_SIZE + + } // end of namespace scribo::convert + +} // end of namespace scribo + +#endif // ! SCRIBO_CONVERT_TO_BASE64_HH diff --git a/scribo/tests/Makefile.am b/scribo/tests/Makefile.am index 1cb222b..09768b1 100644 --- a/scribo/tests/Makefile.am +++ b/scribo/tests/Makefile.am @@ -29,6 +29,7 @@ EXTRA_DIST = \ SUBDIRS = \ binarization \ + convert \ core \ filter \ preprocessing \ diff --git a/scribo/tests/core/Makefile.am b/scribo/tests/convert/Makefile.am similarity index 84% copy from scribo/tests/core/Makefile.am copy to scribo/tests/convert/Makefile.am index 356cc31..c4c912c 100644 --- a/scribo/tests/core/Makefile.am +++ b/scribo/tests/convert/Makefile.am @@ -1,5 +1,4 @@ -# Copyright (C) 2009, 2010 EPITA Research and Development Laboratory -# (LRDE). +# Copyright (C) 2011 EPITA Research and Development Laboratory (LRDE). # # This file is part of Olena. # @@ -20,8 +19,9 @@ include $(top_srcdir)/scribo/tests/tests.mk -check_PROGRAMS = line_info +check_PROGRAMS = \ + base64 -line_info_SOURCES = line_info.cc +base64_SOURCES = base64.cc TESTS = $(check_PROGRAMS) diff --git a/scribo/tests/convert/base64.cc b/scribo/tests/convert/base64.cc new file mode 100644 index 0000000..18d08d9 --- /dev/null +++ b/scribo/tests/convert/base64.cc @@ -0,0 +1,89 @@ +// Copyright (C) 2011 EPITA Research and Development Laboratory (LRDE). +// +// This file is part of Olena. +// +// Olena 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. +// +// Olena is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +// General Public License for more details. +// +// You should have received a copy of the GNU General Public License +// along with Olena. If not, see <http://www.gnu.org/licenses/>. + +/// \file + +#include <cstdio> +#include <cstdlib> + +#include <mln/core/image/image2d.hh> +#include <mln/data/compare.hh> + +#include <mln/io/pbm/load.hh> +#include <mln/io/pgm/load.hh> + +#include <mln/value/int_u.hh> +#include <mln/value/int_u8.hh> + +#include <mln/debug/iota.hh> + +#include <mln/value/int_u16.hh> + +#include <scribo/convert/to_base64.hh> +#include <scribo/convert/from_base64.hh> + +#include "tests/data.hh" + +using namespace mln; + +int main() +{ + + // PBM + { + image2d<bool> ima; + io::pbm::load(ima, SCRIBO_IMG_DIR "/wildly.pbm"); + + util::array<unsigned char> out64; + scribo::convert::to_base64(ima, out64); + + image2d<bool> outbin(ima.domain()); + scribo::convert::from_base64(out64, outbin); + + mln_assertion(outbin == ima); + } + + // PGM (8bits) + { + image2d<value::int_u8> ima; + io::pgm::load(ima, SCRIBO_IMG_DIR "/text_to_group.pgm"); + + util::array<unsigned char> out64; + scribo::convert::to_base64(ima, out64); + + image2d<value::int_u8> outbin(ima.domain()); + scribo::convert::from_base64(out64, outbin); + + mln_assertion(outbin == ima); + } + + // PGM (30bits) + { + image2d<value::int_u<30> > ima(3, 3); + debug::iota(ima, 100000); + + util::array<unsigned char> out64; + scribo::convert::to_base64(ima, out64); + + image2d<value::int_u<30> > outbin(ima.domain()); + scribo::convert::from_base64(out64, outbin); + + mln_assertion(outbin == ima); + } + + + return 0; +} -- 1.5.6.5

1 0

last-svn-commit-764-g004d118 =Add support for whitespace separators visualization.
by Guillaume Lazzara 28 Mar '11

28 Mar '11

* demo/viewer/common.hh, * demo/viewer/key_widget.cc, * demo/viewer/step_widget.cc, * demo/viewer/viewer.cc: Handle visualization. * scribo/toolchain/internal/content_in_doc_functor.hh, * scribo/core/document.hh: Store separator information. * scribo/io/xml/save.hh: Save whitespace separator data. --- scribo/ChangeLog | 14 ++++++ scribo/demo/viewer/common.hh | 22 +++++++++- scribo/demo/viewer/key_widget.cc | 6 ++- scribo/demo/viewer/step_widget.cc | 1 + scribo/demo/viewer/viewer.cc | 20 ++++++++- scribo/scribo/core/document.hh | 47 ++++++++++++++++++++ scribo/scribo/io/xml/save.hh | 18 ++++++++ .../toolchain/internal/content_in_doc_functor.hh | 5 ++- 8 files changed, 128 insertions(+), 5 deletions(-) diff --git a/scribo/ChangeLog b/scribo/ChangeLog index f3f150f..ef97bf9 100644 --- a/scribo/ChangeLog +++ b/scribo/ChangeLog @@ -1,3 +1,17 @@ +2011-02-05 Guillaume Lazzara <z(a)lrde.epita.fr> + + Add support for whitespace separators visualization. + + * demo/viewer/common.hh, + * demo/viewer/key_widget.cc, + * demo/viewer/step_widget.cc, + * demo/viewer/viewer.cc: Handle visualization. + + * scribo/toolchain/internal/content_in_doc_functor.hh, + * scribo/core/document.hh: Store separator information. + + * scribo/io/xml/save.hh: Save whitespace separator data. + 2011-02-18 Guillaume Lazzara <z(a)lrde.epita.fr> * src/text_in_picture.cc: Initialize ImageMagick and fix usage diff --git a/scribo/demo/viewer/common.hh b/scribo/demo/viewer/common.hh index 46f20c1..3b11ba5 100644 --- a/scribo/demo/viewer/common.hh +++ b/scribo/demo/viewer/common.hh @@ -24,14 +24,30 @@ namespace region enum RegionId { + // Text regions + // ------------- + Text = 0, + + // Extension Line, EndOfTextRegion, + // Separators + // ---------- + + Separator, + + // Extension + WhitespaceSeparator, + + EndOfSepsRegion, + + // Misc regions. + // ------------- Image, Noise, - Separator, Table, LineDrawing, Graphic, @@ -40,6 +56,10 @@ namespace region EndOfMiscRegion, + // Typographical lines + // ------------------- + + // Extension Baseline, Meanline, diff --git a/scribo/demo/viewer/key_widget.cc b/scribo/demo/viewer/key_widget.cc index cc10308..3b07617 100644 --- a/scribo/demo/viewer/key_widget.cc +++ b/scribo/demo/viewer/key_widget.cc @@ -22,8 +22,9 @@ KeyWidget::KeyWidget(const region::KeyMap& key_map) : items_(new QTreeWidget()) { item_list_.append(new QTreeWidgetItem(QStringList("Text"))); - item_list_.append(new QTreeWidgetItem(QStringList("Regions"))); - item_list_.append(new QTreeWidgetItem(QStringList("Typographical Lines"))); + item_list_.append(new QTreeWidgetItem(QStringList("Separators"))); + item_list_.append(new QTreeWidgetItem(QStringList("Misc. Regions"))); + item_list_.append(new QTreeWidgetItem(QStringList("Typographical lines"))); QLabel* title = new QLabel(tr("Key")); title->setAlignment(Qt::AlignHCenter); @@ -38,6 +39,7 @@ KeyWidget::KeyWidget(const region::KeyMap& key_map) base_id_.append(0); base_id_.append(region::EndOfTextRegion + 1); + base_id_.append(region::EndOfSepsRegion + 1); base_id_.append(region::EndOfMiscRegion + 1); base_id_.append(region::EndOfTypoRegion + 1); diff --git a/scribo/demo/viewer/step_widget.cc b/scribo/demo/viewer/step_widget.cc index 77e9bd3..19b5d0f 100644 --- a/scribo/demo/viewer/step_widget.cc +++ b/scribo/demo/viewer/step_widget.cc @@ -59,6 +59,7 @@ void StepWidget::activate(QListWidgetItem* item) key = iter.key(); value = iter.value(); + qDebug() << "Loading " << value; emit load_xml(value); } else diff --git a/scribo/demo/viewer/viewer.cc b/scribo/demo/viewer/viewer.cc index 1d48b1a..f34b3e7 100644 --- a/scribo/demo/viewer/viewer.cc +++ b/scribo/demo/viewer/viewer.cc @@ -51,8 +51,11 @@ Viewer::Viewer(int &argc, char** argv) pdialog_(win_) { // Key map + // -------- key_map_[region::Text] = qMakePair(tr("Text Region"), QColor(0, 200, 0)); + + // Extension key_map_[region::Line] = qMakePair(tr("Text line"), QColor(255, 0, 0)); key_map_[region::Image] = qMakePair(tr("Image"), QColor(255, 120, 0)); @@ -65,13 +68,23 @@ Viewer::Viewer(int &argc, char** argv) key_map_[region::Chart] = qMakePair(tr("Chart"), QColor(0, 204, 255)); key_map_[region::Maths] = qMakePair(tr("Maths"), QColor(170, 0, 255)); + // Extension + key_map_[region::WhitespaceSeparator] = qMakePair(tr("Whitespace Separator"), QColor(0, 0, 128)); + + // Extension key_map_[region::Baseline] = qMakePair(tr("Baseline"), QColor(128, 0, 255)); key_map_[region::Meanline] = qMakePair(tr("Meanline"), QColor(128, 0, 255)); + + // Region ids + // ---------- region_ids_["text_region"] = region::Text; + + // Extension region_ids_["line"] = region::Line; + region_ids_["image_region"] = region::Image; region_ids_["noise_region"] = region::Noise; region_ids_["separator_region"] = region::Separator; @@ -81,6 +94,11 @@ Viewer::Viewer(int &argc, char** argv) region_ids_["chart_region"] = region::Chart; region_ids_["maths_region"] = region::Maths; + // Extension + region_ids_["whitespace_separator_region"] = region::WhitespaceSeparator; + + + win_->resize(1152, 864); win_->statusBar(); @@ -572,7 +590,7 @@ Viewer::load_xml(QString filename) while (!region.isNull()) { - if (region.toElement().tagName().contains(QRegExp("(image|graphic|chart|separator|table|text)_region"))) + if (region.toElement().tagName().contains(QRegExp("(whitespace_separator|image|graphic|chart|separator|table|text)_region"))) { QString attr_id = region.toElement().attribute("id", "none"); add_region(region, attr_id); diff --git a/scribo/scribo/core/document.hh b/scribo/scribo/core/document.hh index b547da4..f112410 100644 --- a/scribo/scribo/core/document.hh +++ b/scribo/scribo/core/document.hh @@ -32,6 +32,7 @@ /// \brief Describes document content. # include <mln/core/image/image2d.hh> +# include <mln/core/alias/neighb2d.hh> # include <mln/value/rgb8.hh> # include <mln/io/magick/load.hh> @@ -39,6 +40,8 @@ # include <scribo/core/line_set.hh> # include <scribo/core/paragraph_set.hh> +# include <scribo/primitive/extract/components.hh> + namespace scribo { @@ -83,6 +86,11 @@ namespace scribo const mln::image2d<value::rgb8>& image() const; void set_image(const mln::image2d<value::rgb8>& image); + bool has_whitespace_seps() const; + const mln::image2d<bool>& whitespace_seps() const; + const component_set<L>& whitespace_seps_comps() const; + void set_whitespace_separators(const image2d<bool>& whitespace_seps); + private: const char *filename_; mln::image2d<mln::value::rgb8> image_; @@ -90,6 +98,9 @@ namespace scribo line_set<L> lines_; paragraph_set<L> parset_; component_set<L> elements_; + + mln::image2d<bool> whitespace_seps_; + component_set<L> whitespace_seps_comps_; }; @@ -247,6 +258,42 @@ namespace scribo } + template <typename L> + bool + document<L>::has_whitespace_seps() const + { + return whitespace_seps_.is_valid(); + } + + + template <typename L> + const mln::image2d<bool>& + document<L>::whitespace_seps() const + { + return whitespace_seps_; + } + + + template <typename L> + const component_set<L>& + document<L>::whitespace_seps_comps() const + { + return whitespace_seps_comps_; + } + + + template <typename L> + void + document<L>::set_whitespace_separators(const image2d<bool>& whitespace_seps) + { + whitespace_seps_ = whitespace_seps; + + mln_value(L) ncomps; + whitespace_seps_comps_ = primitive::extract::components(whitespace_seps, + mln::c8(), ncomps); + } + + # endif // ! MLN_INCLUDE_ONLY diff --git a/scribo/scribo/io/xml/save.hh b/scribo/scribo/io/xml/save.hh index 41d4fef..7011e87 100644 --- a/scribo/scribo/io/xml/save.hh +++ b/scribo/scribo/io/xml/save.hh @@ -364,6 +364,24 @@ namespace scribo } + // Whitespace seraparators + if (doc.has_whitespace_seps()) + { + const component_set<L>& + whitespace_seps_comps = doc.whitespace_seps_comps(); + + for_all_comps(c, whitespace_seps_comps) + { + file << " <whitespace_separator_region id=\"wss" + << whitespace_seps_comps(c).id() + << "\">" << std::endl; + + internal::print_box_coords(file, whitespace_seps_comps(c).bbox(), " "); + + file << " </whitespace_separator_region>" << std::endl; + } + } + file << " </page>" << std::endl; file << "</pcGts>" << std::endl; diff --git a/scribo/scribo/toolchain/internal/content_in_doc_functor.hh b/scribo/scribo/toolchain/internal/content_in_doc_functor.hh index fb7cd7c..b8aa56d 100644 --- a/scribo/scribo/toolchain/internal/content_in_doc_functor.hh +++ b/scribo/scribo/toolchain/internal/content_in_doc_functor.hh @@ -237,7 +237,10 @@ namespace scribo if (enable_line_seps) components.add_separators(separators); if (enable_whitespace_seps) + { components.add_separators(whitespaces); + doc.set_whitespace_separators(whitespaces); + } if (enable_debug) mln::io::pbm::save(components.separators(), @@ -251,7 +254,7 @@ namespace scribo on_progress(); - /// Linking potential objects + /// Linking objects on_new_progress_label("Linking objects..."); object_links<L> left_link -- 1.5.6.5

1 0

branch unstable/scribo updated: last-svn-commit-827-g65ec591
by lazzara＠lrde.epita.fr 28 Mar '11

28 Mar '11

This is an automated email from the git hooks/post-receive script. It was generated because a ref change was pushed to the repository containing the project "Olena, a generic and efficient image processing platform". The branch unstable/scribo has been updated discards e58bc06a49ee5020da72efbce8b515a2b9aeb36a (commit) discards 41cec18a096db274554b38e52684f07fc2ff17cf (commit) discards 921edcc8bda188c053965f067c4c425f35d6736a (commit) discards 234857f163935061703e9a266f1d4819853784c2 (commit) discards f74b26eef10f1d8c8d44c0ae6c5a4863e280cc3c (commit) discards 7dcdc997eeb813df22ac5a1838f09ee98f776357 (commit) discards 6c07eb07cb2b526fcc5f6f1e3e9129a909059907 (commit) discards 3c5ade3ef4ade56a212f140ccfaf964f6c045c26 (commit) discards 2021de27002717089153ea8bb6e1eb117e329cb8 (commit) discards b4dcface8e9554a81fd84675f18b2abd6c51cb9e (commit) discards db7457153f9ac3811483be20a4d8981e31443785 (commit) discards 4e7a87b8c9aa19b264a9eaae5fd4eacd7ff7b947 (commit) discards 76d581414104c04a8954b083b24cf9caf58154e7 (commit) discards 1e74eb51d3243487f13ea104079737c53ac0361b (commit) discards 2d12896ac7a0e42de83bed33c3dde02bbae4b6e5 (commit) discards 6adf703bc7b05f9ff00719b7cbbc845a234d3f9d (commit) discards b71d6973bdcfda3c47cc9a4211339555a6cf0a27 (commit) discards 2f870e06bc47707e86500bfb905e013545d81ee0 (commit) discards 4b5b9f8ea9ff23a59ee7bdca6297a57b5b16bdc1 (commit) discards 3f14376ad38b8967e5af7d63ddac93989f58ac39 (commit) discards 8ee4c1acd45d4bd6c1a8805fe41de65c1153ba17 (commit) discards 8aaa787401d5d6681ab824550216d5abee24c324 (commit) discards 3038605191b650a8a86d10ffb986d165bca13f31 (commit) discards eae112f79b28e0e6f217b6cfe130a4a1dc1ca0c4 (commit) discards 294c4219261707af15a0d5593ddefd6f86851c44 (commit) discards 80b10b678600c73da186ebe4662652096c98673b (commit) discards 1a5cc61c52a905239876107d1ac2143a62e23968 (commit) discards 500be97a841a57b0cf6f580d6573a6ef1f941803 (commit) discards 3f06d28a852c01e7f49ec0320a2cdf254ad11ec4 (commit) discards 07b076ce0ba19ac3741350db76a881252cab9313 (commit) discards d045991c53396fcbf462e8824b9bd68657c3824b (commit) discards 9721b83ee36739262562acd9a53019351e476044 (commit) discards 2cd9b0158f329056d6baf732c8c94da4a58f9477 (commit) discards 00e84b1ea30ed7f4d9adb3e46576f0da37d4701b (commit) discards 7a467ce53641d6df7084ad28c230b59e741b3158 (commit) discards c4bfbf3039ad1bc22e9d6a84898e1aa30204b165 (commit) discards 88a5659a616bb9a61144ce29447da7c78afd1d16 (commit) discards 55dec68d501bf9aea0237bc734f8e34a2c2b8659 (commit) discards 525a77d49f93c4d8af8f0f98311a59fa91ad37f5 (commit) discards be7296a994a74454aed04e9ac5697b1ebf7f1239 (commit) discards 3e799ae9a6155fe25743f551e029b8f407ba5f87 (commit) discards c6aef9e87ecd21dc02545f3ff234dfa37c49ef0e (commit) discards 71e09952f8956d7969923783e4d11785ed69ac70 (commit) discards f4cad33327251f4d0d7c9f03ba309b0472671685 (commit) discards 38639f48cf630d9773a72825adf3e1c2bd33d699 (commit) discards 08507d9f6ee6460473604cd94e1cc094ca4dcb6f (commit) discards 300d0d76ad8aba7dbf1f793b8bfbbc32b80016a8 (commit) discards b37a853c16b36dc73376fbc32562772a0a1778eb (commit) discards 5127a7b422860a30f96a86f71f5bb1e6961894fa (commit) discards b1fe7b822ef9667e06e4a61465cca47a19c728d8 (commit) discards 67e03b2fa427dbcea04133c7c62ed6b9e3b40770 (commit) discards 37420bc1bc21b94431344d5ed978f6b537333816 (commit) discards 9fc92d2022701f48b1471d7899df48eefe5c3281 (commit) discards 36bdfe6bd32b4e4fc6f5e4ca6443de39ea7ed1d5 (commit) discards 09b76a65da9f752c14797fe845b5d9f3c2e9e193 (commit) discards 9ce4470df6ec50f7c5776cc78c9ef8b804579b27 (commit) discards cff396c972728565d654eab1ff4258ef18fa51c6 (commit) discards b9a628915f1d9728cacca0049eccb7272427164d (commit) discards 7bdf8a260b084ca369db30a705dd5c3e8a1ecec3 (commit) discards 26501abd4604deb0a0670c6b8bf3a212145477b3 (commit) discards c027c16fdbc3ffe8b1623764a56bd9cfad77a8bc (commit) discards e05c9c33f0bf1a7a3b2499f872f2a4167ceba41f (commit) discards a192077679cb7736a2dc6f096bac377b0f4453ba (commit) discards 209645b7fdd312ecf6b9f6e37281e6b1122792b5 (commit) discards 1cd8d75d23d5d2a54b1847d7ea6bae714b39b37f (commit) discards 47af3d9cb24e89d843ca9648f55db11b575b4bc7 (commit) discards d5019dd2432f7e82eb2ac079a3ab14576b8badb8 (commit) discards c96edd6fb6f8e3ab339b1b565941007a5da9a4c7 (commit) discards 79b3aaa9765b6a9f86d71ddf55d3556d4f922cfd (commit) discards 11325f7f2dd2278993de4dd4a11e9a136617a398 (commit) discards c4bfdc8ca94fc3283920876a447bf21b1efaf9bb (commit) via 65ec591cc15b84468c066dd6708e041b1d3949d1 (commit) via b1edf757ef7afe1323adbac78593d907da3bbb3f (commit) via 59c675bf89f6f708eee6988113338f7b5899807c (commit) via 848f99d169cba718ea39658a3a08527e272144a3 (commit) via 9b60b90c5214d017209f9082558ed25388988863 (commit) via 638a3075e02ea776e2d6e74a2a3d9b8a05d76fde (commit) via 4ad3ae8d2a86ab4192be7392871242e2c9535ce4 (commit) via 31809b6103dcbba82474e951274676b00f315d2f (commit) via 30e9e38e5935bd2305b67bf2c306dafb5fecb047 (commit) via 546e98d51ff890f14e1cb3c367541e9c03725350 (commit) via 485bbf87ecdf4c53bf672cd47e722c7d75703d75 (commit) via 20b750a8628dd43cde273109c57023335c47536d (commit) via 3de602aa446941f8a3ad5d03b5bb2cc031a3bdec (commit) via 91a93e84e31d7571340188f2f1dacdcdb0d6c210 (commit) via abbc1e66aded6326799ed132230fa60bf60b23dd (commit) via 1027aef615d0b8cb373aecc25ca8bab812a3ab03 (commit) via 794a820803ee4bc55872cb49e38a385b6b38b783 (commit) via 5c363a16c9ce736c50e6dcd0e3e7feebd79be7a1 (commit) via b01bf1512d4986dbcc51bfb43f54d7a8b562d38e (commit) via ed1425b584398be6b36be551e7b4258dfd1758a6 (commit) via d31fffd6aad495e8b44b86d3ea667b6d4efa7469 (commit) via 1e9c3e590c82f271e8b0cc8c8b85863d36e91474 (commit) via 65d90390602dde5d14dd25f5ee088b4ac47f47c5 (commit) via ea8ad625701a38fe7980cabc7fd6e8764307b7f4 (commit) via ecf417bbb05bb040a637a71b6d5c5d82164d2ca6 (commit) via 282de701ea7eefc86919581fe6c004ab7cc36584 (commit) via 1d1a977dda81f80570255a3aefa1a8919b9198f1 (commit) via 5db5a7215cc5b5adf1cc2e10b287f854a04a32e2 (commit) via fe898e73cba128d138abb5ae4c8c4aa411c48e77 (commit) via 5b25a55343dd45bc65225697e49fc7af9b35d077 (commit) via 0135714d0d79984802f2f19aa2e93321efeb8802 (commit) via 20da74d6ce217ba0c7300f024c3b174487cb0cd3 (commit) via 881caef92eaa1ad16aa9ae80b26b07fc5a04f191 (commit) via 5c06e0488ea613362d8781d163f87207e83ec58f (commit) via 6de9b0968f12e6bd0c786ad3aeca239f9895efaa (commit) via f92f9d4f33997593565b9bfab782f268786676d4 (commit) via 05a6c098580a1fe9e6ab073a75c48230695473d0 (commit) via 2de39a7ec2fe9a11b20a7771336c70b1556658fd (commit) via 9d82627b1064251d231f796bcd217fa7cdc49c31 (commit) via 95bf4497be229dd5ced2b8e05c04c0372e436509 (commit) via b4f0eefeec21412d670a4c478f5876388e448f9b (commit) via 7c9d3b1c92cc6ba0e952d65f32ed518bb34341cd (commit) via 6b548c5cb710f06612c533b57b39c658a038eb12 (commit) via d12d660ab6cc7611ddd9d3ee29915d5947f7e7e9 (commit) via ca041c01ea50c8fd14779fa5b77586be1ad779be (commit) via ba41452a338d6c4fc8b0963626dfd0a5799b8b76 (commit) via 6fdc4cc496628083dc48e46a6733f35f5a99649a (commit) via 7f4a36790a46eaf04c7b7421b492a6ffe9f9f48e (commit) via e2702750f92e4fe0716aa030b90fd96aa63df100 (commit) via 134e242fedada16527bd7af8cf5bc9e5f66032f1 (commit) via 6985484e9a1b721e6da5bb78ee2222d936d1767a (commit) via 8c287df29ff3049d749db0c0867a4b85f63a5dfb (commit) via fd62480ce9e6a16bb1dc3585ba100d6a9ea6deb1 (commit) via cc8c9ed06e4070b7c0aca23b6d8530fe1f5a9ea0 (commit) via c65020df4f9a43ae7aa49e5d6f7467217be9046d (commit) via 4756e175a1c2614f91be3cf36e129341e375ac43 (commit) via f67cec4c13aa85adffb59cddbf7e0e45925cb5ae (commit) via 2a17f6d9312831e4c9094f40622b90dca8a230ed (commit) via 77429c34a1a3aa4901710880d612e7ad3949228b (commit) via 8f266e9124f39e2d5592ca4dfc914d784ea3f579 (commit) via 5dbed1ab586fba85cff78903469e6a4015bbb509 (commit) via 959710dac03a9bcd569d14a2d53a6ca149214196 (commit) via d3a06bf8f609f7c90871f6bc09b6a37d97ebd972 (commit) via 004d118aeb91bd85b36a2379bb7546e37a785189 (commit) via 12c45b02b83d3d06505b7f5f8f56c1f2c5b32d41 (commit) via e5c41a61332676c03a8bf6771ddddddaa23a2654 (commit) via f54c0a6c44a5dee7a2bdec4480d98cdeb52d7f57 (commit) via e01df8b1b88b2757f236e2f8b745d164c7ff2cc3 (commit) via e026707a6679a82e6d183d925a9fef8ad045208a (commit) via bc82f1691d64d78fb60795be37553d84257995ef (commit) via 9e5a4bf678f40e84f65f2fd2c2383b5b8869ae5b (commit) This update added new revisions after undoing existing revisions. That is to say, the old revision is not a strict subset of the new revision. This situation occurs when you --force push a change and generate a repository containing something like this: * -- * -- B -- O -- O -- O (e58bc06a49ee5020da72efbce8b515a2b9aeb36a) \ N -- N -- N (65ec591cc15b84468c066dd6708e041b1d3949d1) When this happens we assume that you've already had alert emails for all of the O revisions, and so we here report only the revisions in the N branch from the common base, B. Those revisions listed above that are new to this repository have not appeared on any other notification email; so we list those revisions in full, below. - Log ----------------------------------------------------------------- 65ec591 demo/viewer/xml_widget.cc: Fix a warning. b1edf75 demo/viewer/runner.cc: Improve progress notification. 59c675b Fix compilation issues on MAC. 848f99d scribo/primitive/link/internal/dmax_functor_base.hh: Make the dmax ratio safer. 9b60b90 scribo/text/merging: Add a precondition. Fix merging policy. 638a307 scribo/primitive/link/internal/link_functor_base.hh: Stop neighbor lookup when a separator is found. 4ad3ae8 Regen generated files. 31809b6 Fix namespace ambiguities. 30e9e38 src/Makefile.am: define HAVE_QT for content_in_doc. 546e98d Add missing anchor argument. 485bbf8 Regen generated files. 20b750a mln/labeling/colorize.hh: Add a missing inline. 3de602a Add more from_to overloards. 91a93e8 build-aux/build_unit_test.sh: Define HAVE_* for unit-tests. abbc1e6 Regen generated files. 1027aef tests/toolchain/nepomuk/Makefile.am: Add MAGICKXX flags. 794a820 scribo/core/def/lbl_type.hh: Use int_u<n> as label type. 5c363a1 Set unit tests dependencies. b01bf15 New debug tools. ed1425b New non-text components extraction routine. d31fffd Introduce result image output. 1e9c3e5 Save image edge coordinates in XML output. 65d9039 scribo/filter/object_links_aligned.hh: New. ea8ad62 scribo/primitive/extract/separators_nonvisible.hh: Cleanup and improve debug support. ecf417b Various small fixes. 282de70 Introduce a new component linking method. 1d1a977 Spread anchor value to more methods in link functors. 5db5a72 Introduce a logger class. fe898e7 Introduce a logger class. 5b25a55 Introduce new anchors. 0135714 Rename document serializer base class. 20da74d Store more information in scribo::document. 881caef Rename line_info::components() to line_info::component_ids. 5c06e04 Some changes in debug routines. 6de9b09 Add HAVE_QT guards. f92f9d4 Small fixes in viewer. 05a6c09 scribo/io/xml/internal/extended_page_xml_visitor.hh: Save separators data. 2de39a7 scribo/io/xml/internal/full_xml_visitor.hh: Do not copy image data. 9d82627 Make OCR step optional in viewer. 95bf449 scribo/toolchain/internal/content_in_doc_functor.hh: Make OCR step optional. b4f0eef Compress image data in XML output. 7c9d3b1 Small fixes in Scribo. 6b548c5 Regen mk files. d12d660 scribo/primitive/extract/non_text.hh: Remove debug. ca041c0 Add new debug tools. ba41452 scribo/text/extract_lines.hh: Update code. 6fdc4cc Make use of mln::fun::v2v::rgb_to_luma. 7f4a367 mln/labeling/fill_holes.hh: Improve speed. e270275 mln/fun/v2v/rgb_to_luma.hh: New function for grayscale conversion. 134e242 scribo/io/xml/load.hh: New XML loader. 6985484 Make XML output more flexible. 8c287df Set component type during component extraction. fd62480 configure.ac: scribo/src/primitive/remove. cc8c9ed Add new tools in Scribo. c65020d Small fixes in Scribo. 4756e17 Improve and cleanup whitespace separator detection. f67cec4 Add new conversion routines from string to tag. 2a17f6d Various changes in scribo core structures. 77429c3 Rename files in Scribo. 8f266e9 mln/util/array.hh: Add last() method. 5dbed1a Add an optional base index for debug::iota. 959710d configure.ac: configure scribo/tests/convert. d3a06bf Add Base64 conversion routines. 004d118 =Add support for whitespace separators visualization. 12c45b0 Deactivate erroneous assertion in regional_maxima.hh. ----------------------------------------------------------------------- Summary of changes: hooks/post-receive -- Olena, a generic and efficient image processing platform

1 0

last-svn-commit-686-g3856477 Do not negate Sauvola's output.
by Guillaume Lazzara 28 Mar '11

28 Mar '11

* scribo/toolchain/text_in_doc_preprocess.hh, * scribo/toolchain/text_in_picture.hh: Do not negate Sauvola's output anymore. --- scribo/scribo/toolchain/text_in_picture.hh | 37 ++++++++++++++++++---------- 1 files changed, 24 insertions(+), 13 deletions(-) diff --git a/scribo/scribo/toolchain/text_in_picture.hh b/scribo/scribo/toolchain/text_in_picture.hh index 18d3a8e..f5fa5ba 100644 --- a/scribo/scribo/toolchain/text_in_picture.hh +++ b/scribo/scribo/toolchain/text_in_picture.hh @@ -249,21 +249,32 @@ namespace scribo timer_.restart(); mln_ch_value(I,bool) input; - unsigned w = win; - if (!w) - w = std::min(intensity_ima.nrows() / 3, intensity_ima.ncols() / 3); - if (! w % 2) - ++w; - w = std::min(w, conf.sauvola_min_w); - if (multi_scale_bin) - { - std::cout << "** Using sauvola_ms with w_1 = " << w << std::endl; - input = scribo::binarization::sauvola_ms(intensity_ima, w, conf.sauvola_s); - } + + + unsigned w = std::min(intensity_ima.nrows() / 3, intensity_ima.ncols() / 3); + if (win) + input = scribo::binarization::sauvola_ms_split(input_rgb, w, + conf.sauvola_s, 1); else { - std::cout << "** Using sauvola with w_1 = " << w << std::endl; - input = scribo::binarization::sauvola(intensity_ima, w); + + unsigned w = win; + if (!w) + w = std::min(intensity_ima.nrows() / 3, intensity_ima.ncols() / 3); + if (! w % 2) + ++w; + w = std::min(w, conf.sauvola_min_w); + + if (multi_scale_bin) + { + std::cout << "** Using sauvola_ms with w_1 = " << w << std::endl; + input = scribo::binarization::sauvola_ms(intensity_ima, w, conf.sauvola_s); + } + else + { + std::cout << "** Using sauvola with w_1 = " << w << std::endl; + input = scribo::binarization::sauvola(intensity_ima, w); + } } if (debug) -- 1.5.6.5

1 0

last-svn-commit-685-g0af6845 Change Sauvola's window size for reverted image and filter width ratio.
by Guillaume Lazzara 28 Mar '11

28 Mar '11

--- scribo/scribo/toolchain/text_in_picture.hh | 11 +++++++++-- scribo/src/text_in_picture_neg.cc | 3 +++ 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/scribo/scribo/toolchain/text_in_picture.hh b/scribo/scribo/toolchain/text_in_picture.hh index 19af9e3..18d3a8e 100644 --- a/scribo/scribo/toolchain/text_in_picture.hh +++ b/scribo/scribo/toolchain/text_in_picture.hh @@ -103,6 +103,7 @@ namespace scribo component_set<mln_ch_value(I, value::label_16)> text_in_picture(const Image& input_rgb_orig, bool bg_removal, bool multi_scale_bin, + unsigned win = 0, unsigned max_dim_size = 0, unsigned lambda = 0, const char *debug_outdir = 0); @@ -136,7 +137,7 @@ namespace scribo // Group Filtering bbox_h_ratio = 1.75f; - bbox_overlap = 0.80f; + bbox_overlap = 0.60f; small_groups = 3; v_thickness = 8; regroup_dmax = 30; @@ -167,6 +168,7 @@ namespace scribo component_set<mln_ch_value(I, value::label_16)> text_in_picture(const Image& input_rgb_orig_, bool bg_removal, bool multi_scale_bin, + unsigned win = 0, unsigned max_dim_size = 0, unsigned lambda = 0, const char *debug_outdir = 0) { @@ -246,7 +248,10 @@ namespace scribo // Binarize foreground to use it in the processing chain. timer_.restart(); mln_ch_value(I,bool) input; - unsigned w = std::min(intensity_ima.nrows() / 3, intensity_ima.ncols() / 3); + + unsigned w = win; + if (!w) + w = std::min(intensity_ima.nrows() / 3, intensity_ima.ncols() / 3); if (! w % 2) ++w; w = std::min(w, conf.sauvola_min_w); @@ -347,6 +352,8 @@ namespace scribo hratio_filtered_links = filter::object_links_bbox_h_ratio(merged_links, conf.bbox_h_ratio); + hratio_filtered_links = + filter::object_links_bbox_w_ratio(hratio_filtered_links, 3); diff --git a/scribo/src/text_in_picture_neg.cc b/scribo/src/text_in_picture_neg.cc index 7d6694a..8b80b43 100644 --- a/scribo/src/text_in_picture_neg.cc +++ b/scribo/src/text_in_picture_neg.cc @@ -82,6 +82,7 @@ #include <scribo/filter/object_groups_with_holes.hh> #include <scribo/filter/object_links_bbox_h_ratio.hh> +#include <scribo/filter/object_links_bbox_w_ratio.hh> #include <scribo/filter/object_links_bbox_overlap.hh> #include <scribo/filter/common/objects_photo.hh> @@ -166,6 +167,7 @@ int main(int argc, char* argv[]) typedef image2d<value::label_16> L; component_set<L> comps = toolchain::text_in_picture(input_rgb, bg_removal, multi_scale_bin, + 0, max_dim_size, lambda, out_base_dir); @@ -174,6 +176,7 @@ int main(int argc, char* argv[]) comps_neg = toolchain::text_in_picture(world::rgb::invert(input_rgb), bg_removal, multi_scale_bin, + 15, max_dim_size, lambda, out_base_dir); -- 1.5.6.5

1 0

last-svn-commit-684-gcd88039 Improve text_in_picture_neg
by Guillaume Lazzara 28 Mar '11

28 Mar '11

--- scribo/scribo/toolchain/text_in_picture.hh | 2 +- 1 files changed, 1 insertions(+), 1 deletions(-) diff --git a/scribo/scribo/toolchain/text_in_picture.hh b/scribo/scribo/toolchain/text_in_picture.hh index 9746645..19af9e3 100644 --- a/scribo/scribo/toolchain/text_in_picture.hh +++ b/scribo/scribo/toolchain/text_in_picture.hh @@ -135,7 +135,7 @@ namespace scribo sauvola_min_w = 51u; // Group Filtering - bbox_h_ratio = 1.60f; + bbox_h_ratio = 1.75f; bbox_overlap = 0.80f; small_groups = 3; v_thickness = 8; -- 1.5.6.5

1 0

last-svn-commit-683-gd6c8fae Improve reconstruction?
by Guillaume Lazzara 28 Mar '11

28 Mar '11

--- scribo/scribo/primitive/extract/lines_h_pattern.hh | 2 +- scribo/scribo/primitive/extract/lines_v_pattern.hh | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/scribo/scribo/primitive/extract/lines_h_pattern.hh b/scribo/scribo/primitive/extract/lines_h_pattern.hh index 6a1f7f0..28be492 100644 --- a/scribo/scribo/primitive/extract/lines_h_pattern.hh +++ b/scribo/scribo/primitive/extract/lines_h_pattern.hh @@ -106,7 +106,7 @@ namespace scribo mln_concrete(I) output = lines_pattern(input, length, 1, win); - unsigned new_length = length / 2 + delta; + unsigned new_length = length + delta; new_length += 1 - (new_length % 2); // Guaranty that new_length is odd. mln_concrete(I) diff --git a/scribo/scribo/primitive/extract/lines_v_pattern.hh b/scribo/scribo/primitive/extract/lines_v_pattern.hh index 8a103ac..ada70eb 100644 --- a/scribo/scribo/primitive/extract/lines_v_pattern.hh +++ b/scribo/scribo/primitive/extract/lines_v_pattern.hh @@ -88,7 +88,7 @@ namespace scribo mln_concrete(I) output = lines_pattern(input, length, 0, win); - unsigned new_length = length / 2 + delta; + unsigned new_length = length + delta; new_length += 1 - (new_length % 2); // Guaranty that new_length is odd. mln_concrete(I) -- 1.5.6.5

1 0

last-svn-commit-682-ga0d5c6a Improve output of white space algorithm.
by Guillaume Lazzara 28 Mar '11

28 Mar '11

--- scribo/sandbox/z/white_spaces/white_spaces.cc | 45 ++++++++++++++++---- .../scribo/primitive/group/from_double_link_any.hh | 20 +++++---- 2 files changed, 48 insertions(+), 17 deletions(-) diff --git a/scribo/sandbox/z/white_spaces/white_spaces.cc b/scribo/sandbox/z/white_spaces/white_spaces.cc index 54ef436..d32a631 100644 --- a/scribo/sandbox/z/white_spaces/white_spaces.cc +++ b/scribo/sandbox/z/white_spaces/white_spaces.cc @@ -59,8 +59,6 @@ #include <scribo/primitive/group/from_double_link_any.hh> -#include <scribo/primitive/group/from_single_link.hh> - #include <scribo/filter/object_links_top_aligned.hh> #include <scribo/filter/object_groups_small.hh> #include <scribo/filter/object_links_bottom_aligned.hh> @@ -411,6 +409,17 @@ int main(int argc, char *argv[]) gt.start(); + + // Remove horizontal lines. + t.restart(); + + image2d<bool> hlines = primitive::extract::lines_h_pattern(input, 50, 3); + input = primitive::remove::separators(input, hlines); + + t_ = t; + std::cout << "Horizontal lines removed - " << t_ << std::endl; + + // Closing structural - Connect characters. t.restart(); @@ -832,12 +841,32 @@ int main(int argc, char *argv[]) io::pbm::save(output, "separators_hom.pbm"); io::pbm::save(separators, "separators_filtered.pbm"); } - } - t_ = t; - std::cout << "Separator image - " << t_ << std::endl; + t.restart(); + value::int_u16 ncomps; + component_set<L> comps = primitive::extract::components(output, c8(), ncomps); + image2d<value::rgb8> both; + + both = data::convert(value::rgb8(), input); + + // Needed since the rotated image origin is (0,0). Rotation does + // not preserve rotated coordinates. + dpoint2d dp(input.domain().pcenter() - input_clo.domain().pcenter()); + + for_all_comps(c, comps) + { + box2d b = geom::rotate(comps(c).bbox(), -90, input_clo.domain().pcenter()); + mln::draw::line(both, + b.pmin() + dp, + b.pmax() + dp, + literal::green); + } + t_ = t; + std::cout << "Output image - " << t_ << std::endl; + gt.stop(); + t_ = gt; + std::cout << "Total time: " << t_ << std::endl; - gt.stop(); - t_ = gt; - std::cout << "Total time: " << t_ << std::endl; + io::ppm::save(both, argv[5]); + } } diff --git a/scribo/scribo/primitive/group/from_double_link_any.hh b/scribo/scribo/primitive/group/from_double_link_any.hh index b3bd82a..300ecd6 100644 --- a/scribo/scribo/primitive/group/from_double_link_any.hh +++ b/scribo/scribo/primitive/group/from_double_link_any.hh @@ -98,16 +98,18 @@ namespace scribo else parent(pi) = pli; } - - pi = internal::find_root(parent, i); - unsigned pri = internal::find_root(parent, right_link(i)); - - if (pi != pri) + else { - if (pri < pi) - parent(pri) = pi; - else - parent(pi) = pri; + pi = internal::find_root(parent, i); + unsigned pri = internal::find_root(parent, right_link(i)); + + if (pi != pri) + { + if (pri < pi) + parent(pri) = pi; + else + parent(pi) = pri; + } } } -- 1.5.6.5

1 0

last-svn-commit-681-g7840dad sandbox/z/white_spaces/white_spaces.cc: Fix compilation.
by Guillaume Lazzara 28 Mar '11

28 Mar '11

--- scribo/sandbox/z/white_spaces/white_spaces.cc | 3 ++- 1 files changed, 2 insertions(+), 1 deletions(-) diff --git a/scribo/sandbox/z/white_spaces/white_spaces.cc b/scribo/sandbox/z/white_spaces/white_spaces.cc index d832d58..54ef436 100644 --- a/scribo/sandbox/z/white_spaces/white_spaces.cc +++ b/scribo/sandbox/z/white_spaces/white_spaces.cc @@ -470,7 +470,8 @@ int main(int argc, char *argv[]) // Right mln::single_right_dmax_ratio_aligned_functor<L> functor(input_clo, components, dmax, min_angle, max_angle, anchor::Top); - top_right = primitive::link::impl::compute_fastest(functor, anchor::Top); +// top_right = primitive::link::impl::compute_fastest(functor, anchor::Top); + top_right = primitive::link::compute(functor, anchor::Top); t.stop(); -- 1.5.6.5

1 0

last-svn-commit-680-g7f18abf Backup FineReader XML schema
by Guillaume Lazzara 28 Mar '11

28 Mar '11

--- scribo/sandbox/z/FineReader9-schema-v1.xml | 447 ++++++++++++++++++++++++++++ 1 files changed, 447 insertions(+), 0 deletions(-) create mode 100644 scribo/sandbox/z/FineReader9-schema-v1.xml diff --git a/scribo/sandbox/z/FineReader9-schema-v1.xml b/scribo/sandbox/z/FineReader9-schema-v1.xml new file mode 100644 index 0000000..6c8beb2 --- /dev/null +++ b/scribo/sandbox/z/FineReader9-schema-v1.xml @@ -0,0 +1,447 @@ +<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema" + targetNamespace="http://www.abbyy.com/FineReader_xml/FineReader9-schema-v1.xml" + xmlns:tns="http://www.abbyy.com/FineReader_xml/FineReader9-schema-v1.xml" + elementFormDefault="qualified"> + <xs:annotation> + <xs:documentation xml:lang="en">Schema for representing OCR results exported from FineReader 9.0 SDK. Copyright 2001-2007 ABBYY, Inc. + </xs:documentation> + </xs:annotation> + + <xs:element name="document"> + <xs:complexType> + <xs:sequence> + <xs:element name="documentData" minOccurs="0" maxOccurs="1"> + <xs:annotation> + <xs:documentation xml:lang="en">Global document data + </xs:documentation> + </xs:annotation> + <xs:complexType> + <xs:sequence> + <xs:element name="fontStyles" minOccurs="0" maxOccurs="1"> + <xs:annotation> + <xs:documentation xml:lang="en">Font formatting styles collection + </xs:documentation> + </xs:annotation> + <xs:complexType> + <xs:sequence> + <xs:element name="fontStyle" minOccurs="0" maxOccurs="unbounded" type="tns:FontStyleType"> + <xs:annotation> + <xs:documentation xml:lang="en">Font formatting style + </xs:documentation> + </xs:annotation> + </xs:element> + </xs:sequence> + </xs:complexType> + </xs:element> + <xs:element name="paragraphStyles" minOccurs="0" maxOccurs="1"> + <xs:annotation> + <xs:documentation xml:lang="en">Paragraph formatting styles collection + </xs:documentation> + </xs:annotation> + <xs:complexType> + <xs:sequence> + <xs:element name="paragraphStyle" minOccurs="0" maxOccurs="unbounded" type="tns:ParagraphStyleType"> + <xs:annotation> + <xs:documentation xml:lang="en">Paragraph formatting style + </xs:documentation> + </xs:annotation> + </xs:element> + </xs:sequence> + </xs:complexType> + </xs:element> + <xs:element name="sections" minOccurs="0" maxOccurs="1"> + <xs:annotation> + <xs:documentation xml:lang="en">Document sections collection + </xs:documentation> + </xs:annotation> + <xs:complexType> + <xs:sequence> + <xs:element name="section" minOccurs="0" maxOccurs="unbounded" type="tns:SectionType"> + <xs:annotation> + <xs:documentation xml:lang="en">Section + </xs:documentation> + </xs:annotation> + </xs:element> + </xs:sequence> + </xs:complexType> + </xs:element> + </xs:sequence> + </xs:complexType> + </xs:element> + <xs:element name="page" minOccurs="0" maxOccurs="unbounded"> + <xs:annotation> + <xs:documentation xml:lang="en">Recognized page + </xs:documentation> + </xs:annotation> + <xs:complexType> + <xs:sequence> + <xs:element name="block" minOccurs="0" maxOccurs="unbounded" type="tns:BlockType"> + <xs:annotation> + <xs:documentation xml:lang="en">Recognized block + </xs:documentation> + </xs:annotation> + </xs:element> + </xs:sequence> + <xs:attribute name="width" type="xs:integer" use="required"/> + <xs:attribute name="height" type="xs:integer" use="required"/> + <xs:attribute name="resolution" type="xs:integer" use="required"/> + <xs:attribute name="originalCoords" type="xs:boolean" use="optional" default="false"> + <xs:annotation> + <xs:documentation xml:lang="en">If true, all coordinates are relative to original image before opening, otherwise they are relative to the opened (deskewed) image</xs:documentation> + </xs:annotation> + </xs:attribute> + </xs:complexType> + </xs:element> + </xs:sequence> + <xs:attribute name="version" type="xs:string" use="required"/> + <xs:attribute name="producer" type="xs:string" use="required"/> + <xs:attribute name="pagesCount" type="xs:integer" use="optional" default="1"/> + <xs:attribute name="mainLanguage" type="xs:string" use="optional"/> + <xs:attribute name="languages" type="xs:string" use="optional"/> + </xs:complexType> + </xs:element> + + <xs:complexType name ="ParagraphStyleType"> + <xs:attribute name="id" type="xs:integer" use="required" /> + <xs:attribute name="name" type="xs:string" use="required" /> + <xs:attribute name="mainFontStyleId" type="xs:integer" use="required" /> + <xs:attribute name="role" use="required"> + <xs:simpleType> + <xs:restriction base="xs:string"> + <xs:enumeration value="text"/> + <xs:enumeration value="tableText"/> + <xs:enumeration value="heading"/> + <xs:enumeration value="tableHeading"/> + <xs:enumeration value="pictureCaption"/> + <xs:enumeration value="tableCaption"/> + <xs:enumeration value="footnote" /> + <xs:enumeration value="endnote" /> + <xs:enumeration value="rt" /> + <xs:enumeration value="garb" /> + <xs:enumeration value="other" /> + </xs:restriction> + </xs:simpleType> + </xs:attribute> + <xs:attribute name="roleLevel" type="xs:integer" use="optional" default="-1" /> + <xs:attribute name="align" type="tns:ParagraphAlignment" use="required" /> + <xs:attribute name="width" type="xs:integer" use="optional" default="-1" /> + <xs:attribute name="before" type="xs:integer" use="optional" default="-1" /> + <xs:attribute name="after" type="xs:integer" use="optional" default="-1" /> + <xs:attribute name="lineSpacing" type="xs:integer" use="optional" default="0" /> + <xs:attribute name="startIndent" type="xs:integer" use="required"/> + </xs:complexType> + + <xs:complexType name="FontStyleType"> + <xs:attribute name="id" type="xs:integer" use="required" /> + <xs:attribute name="name" type="xs:string" use="required" /> + <xs:attribute name="italic" type="xs:boolean" use="optional" default="false" /> + <xs:attribute name="bold" type="xs:boolean" use="optional" default="false"/> + <xs:attribute name="smallcaps" type="xs:boolean" use="optional" default="false"/> + <xs:attribute name="scaling" type="xs:integer" use="optional" default="1000" /> + <xs:attribute name="spacing" type="xs:integer" use="optional" default="0" /> + <xs:attribute name="ff" type="xs:string" use="required"/> + <xs:attribute name="fs" type="xs:integer" use="required"/> +</xs:complexType> + + <xs:complexType name="SectionType"> + <xs:sequence> + <xs:element name="stream" minOccurs="0" maxOccurs="unbounded" type="tns:TextStreamType"> + <xs:annotation> + <xs:documentation xml:lang="en">Text Stream is the sequence of paragraphs and/or blocks + </xs:documentation> + </xs:annotation> + </xs:element> + </xs:sequence> + </xs:complexType> + + <xs:complexType name="TextStreamType"> + <xs:sequence> + <xs:element name="parId" minOccurs="0" maxOccurs="unbounded"> + <xs:annotation> + <xs:documentation xml:lang="en">Id of paragraph or block + </xs:documentation> + </xs:annotation> + <xs:complexType> + <xs:attribute name="id" type="xs:string" use="required" /> + </xs:complexType> + </xs:element> + </xs:sequence> + <xs:attribute name="role" use="optional" default="text"> + <xs:simpleType> + <xs:restriction base="xs:string"> + <xs:enumeration value="undef" /> + <xs:enumeration value="garb" /> + <xs:enumeration value="text" /> + <xs:enumeration value="footnote" /> + <xs:enumeration value="endnote" /> + <xs:enumeration value="incut" /> + <xs:enumeration value="rt" /> + </xs:restriction> + </xs:simpleType> + </xs:attribute> + <xs:attribute name="rtId" type="xs:integer" use="optional" default="0" /> + <xs:attribute name="prevPar" type="xs:string" use="optional" default="" /> + <xs:attribute name="nextPar" type="xs:string" use="optional" default="" /> + </xs:complexType> + + <xs:complexType name="BlockType"> + <xs:sequence> + <xs:element name="region" minOccurs="1" maxOccurs="1"> + <xs:annotation> + <xs:documentation xml:lang="en">Block region, the set of rectangles + </xs:documentation> + </xs:annotation> + <xs:complexType> + <xs:sequence> + <xs:element name="rect" minOccurs="1" maxOccurs="unbounded"> + <xs:complexType> + <xs:attribute name="l" type="xs:integer" use="required"/> + <xs:attribute name="t" type="xs:integer" use="required"/> + <xs:attribute name="r" type="xs:integer" use="required"/> + <xs:attribute name="b" type="xs:integer" use="required"/> + </xs:complexType> + </xs:element> + </xs:sequence> + </xs:complexType> + </xs:element> + <xs:element name="text" minOccurs="0" maxOccurs="1" type="tns:TextType"> + <xs:annotation> + <xs:documentation xml:lang="en">Recognized block text, presents if blockType attribute is Text</xs:documentation> + </xs:annotation> + </xs:element> + <xs:element name="row" minOccurs="0" maxOccurs="unbounded" type="tns:TableRowType"> + <xs:annotation> + <xs:documentation xml:lang="en">The set of table rows, presents if blockType attribute is Table</xs:documentation> + </xs:annotation> + </xs:element> + </xs:sequence> + <xs:attribute name="blockType" use="required"> + <xs:simpleType> + <xs:restriction base="xs:string"> + <xs:enumeration value="Text"/> + <xs:enumeration value="Table"/> + <xs:enumeration value="Picture"/> + <xs:enumeration value="Barcode"/> + </xs:restriction> + </xs:simpleType> + </xs:attribute> + <xs:attribute name="blockName" type="xs:string" use="optional"/> + <xs:attribute name="isHidden" type="xs:boolean" use="optional" default="false"/> + <xs:attribute name="l" type="xs:integer" use="required"/> + <xs:attribute name="t" type="xs:integer" use="required"/> + <xs:attribute name="r" type="xs:integer" use="required"/> + <xs:attribute name="b" type="xs:integer" use="required"/> + </xs:complexType> + + + + <xs:complexType name="TextType"> + <xs:sequence> + <xs:element name="par" minOccurs="0" maxOccurs="unbounded" type="tns:ParagraphType"> + <xs:annotation> + <xs:documentation xml:lang="en">Text paragraph</xs:documentation> + </xs:annotation> + </xs:element> + </xs:sequence> + <xs:attribute name="orientation" use="optional" default="Normal"> + <xs:simpleType> + <xs:restriction base="xs:string"> + <xs:enumeration value="Normal"/> + <xs:enumeration value="RotatedClockwise"/> + <xs:enumeration value="RotatedUpsidedown"/> + <xs:enumeration value="RotatedCounterclockwise"/> + </xs:restriction> + </xs:simpleType> + </xs:attribute> + <xs:attribute name="backgroundColor" type="xs:integer" use="optional" default="16777215"/> + <xs:attribute name="mirrored" type="xs:boolean" use="optional" default="false"/> + <xs:attribute name="inverted" type="xs:boolean" use="optional" default="false"/> + </xs:complexType> + + + <xs:complexType name="TableRowType"> + <xs:sequence> + <xs:element name="cell" minOccurs="0" maxOccurs="unbounded"> + <xs:annotation> + <xs:documentation xml:lang="en">Table cell</xs:documentation> + </xs:annotation> + <xs:complexType> + <xs:sequence> + <xs:element name="text" minOccurs="0" maxOccurs="unbounded" type="tns:TextType"> + <xs:annotation> + <xs:documentation xml:lang="en">Cell text</xs:documentation> + </xs:annotation> + </xs:element> + </xs:sequence> + <xs:attribute name="colSpan" type="xs:integer" use="optional" default="1"/> + <xs:attribute name="rowSpan" type="xs:integer" use="optional" default="1"/> + <xs:attribute name="align" use="optional" default="Top"> + <xs:simpleType> + <xs:restriction base="xs:string"> + <xs:enumeration value="Top"/> + <xs:enumeration value="Center"/> + <xs:enumeration value="Bottom"/> + </xs:restriction> + </xs:simpleType> + </xs:attribute> + <xs:attribute name="picture" type="xs:boolean" use="optional" default="false"/> + <xs:attribute name="leftBorder" use="optional" type="tns:TableCellBorderType" default="Black"/> + <xs:attribute name="topBorder" use="optional" type="tns:TableCellBorderType" default="Black"/> + <xs:attribute name="rightBorder" use="optional" type="tns:TableCellBorderType" default="Black"/> + <xs:attribute name="bottomBorder" use="optional" type="tns:TableCellBorderType" default="Black"/> + <xs:attribute name="width" type="xs:integer" use="required"/> + <xs:attribute name="height" type="xs:integer" use="required"/> + </xs:complexType> + </xs:element> + </xs:sequence> + </xs:complexType> + + + <xs:complexType name="ParagraphType"> + <xs:sequence> + <xs:element name="line" minOccurs="0" maxOccurs="unbounded" type="tns:LineType"> + <xs:annotation> + <xs:documentation xml:lang="en">Text paragraph line</xs:documentation> + </xs:annotation> + </xs:element> + </xs:sequence> + <xs:attribute name="dropCapCharsCount" type="xs:integer" use="optional" default="0"/> + <xs:attribute name="dropCap-l" type="xs:integer" use="optional"/> + <xs:attribute name="dropCap-t" type="xs:integer" use="optional"/> + <xs:attribute name="dropCap-r" type="xs:integer" use="optional"/> + <xs:attribute name="dropCap-b" type="xs:integer" use="optional"/> + <xs:attribute name="align" type="tns:ParagraphAlignment" use="optional" default="Left" /> + <xs:attribute name="leftIndent" type="xs:integer" use="optional" default="0"/> + <xs:attribute name="rightIndent" type="xs:integer" use="optional" default="0"/> + <xs:attribute name="startIndent" type="xs:integer" use="optional" default="0"/> + <xs:attribute name="lineSpacing" type="xs:integer" use="optional" default="0"/> + <xs:attribute name="id" type="xs:string" use="optional" /> + <xs:attribute name="style" type="xs:integer" use="optional" /> + </xs:complexType> + +<xs:simpleType name="ParagraphAlignment"> + <xs:restriction base="xs:string"> + <xs:enumeration value="Left"/> + <xs:enumeration value="Center"/> + <xs:enumeration value="Right"/> + <xs:enumeration value="Justified"/> + </xs:restriction> +</xs:simpleType> + + <xs:complexType name="LineType"> + <xs:sequence> + <xs:element name="formatting" minOccurs="0" maxOccurs="unbounded" type="tns:FormattingType"> + <xs:annotation> + <xs:documentation xml:lang="en">Group of characters with uniform formatting</xs:documentation> + </xs:annotation> + </xs:element> + </xs:sequence> + <xs:attribute name="baseline" type="xs:integer" use="required"/> + <xs:attribute name="l" type="xs:integer" use="required"/> + <xs:attribute name="t" type="xs:integer" use="required"/> + <xs:attribute name="r" type="xs:integer" use="required"/> + <xs:attribute name="b" type="xs:integer" use="required"/> + </xs:complexType> + + <xs:complexType name="FormattingType" mixed="true"> + <xs:sequence> + <xs:choice minOccurs="0" maxOccurs="unbounded"> + <xs:annotation> + <xs:documentation xml:lang="en">Attributes of characters are alternated with word's recognition variants. The variants of recognition of the word are written before the word</xs:documentation> + </xs:annotation> + <xs:element name="charParams" type="tns:CharParamsType"> + <xs:annotation> + <xs:documentation xml:lang="en">Attributes of single character</xs:documentation> + </xs:annotation> + </xs:element> + <xs:element name="wordRecVariants"> + <xs:annotation> + <xs:documentation xml:lang="en">Variants of recognition of the next word</xs:documentation> + </xs:annotation> + <xs:complexType> + <xs:sequence> + <xs:element name="wordRecVariant" minOccurs="0" maxOccurs="unbounded" type="tns:WordRecognitionVariant"/> + </xs:sequence> + </xs:complexType> + </xs:element> + </xs:choice> + </xs:sequence> + <xs:attribute name="lang" type="xs:string" use="required"/> + <xs:attribute name="ff" type="xs:string" use="optional"/> + <xs:attribute name="fs" type="xs:float" use="optional"/> + <xs:attribute name="bold" type="xs:boolean" use="optional" default="false"/> + <xs:attribute name="italic" type="xs:boolean" use="optional" default="false"/> + <xs:attribute name="subscript" type="xs:boolean" use="optional" default="false"/> + <xs:attribute name="superscript" type="xs:boolean" use="optional" default="false"/> + <xs:attribute name="smallcaps" type="xs:boolean" use="optional" default="false"/> + <xs:attribute name="underline" type="xs:boolean" use="optional" default="false"/> + <xs:attribute name="strikeout" type="xs:boolean" use="optional" default="false"/> + <xs:attribute name="color" type="xs:integer" use="optional" default="0"/> + <xs:attribute name="scaling" type="xs:integer" use="optional" default="1000"/> + <xs:attribute name="spacing" type="xs:integer" use="optional" default="0"/> + </xs:complexType> + + <xs:complexType name="WordRecognitionVariant"> + <xs:sequence> + <xs:element name="variantText" minOccurs="1" maxOccurs="1"> + <xs:complexType mixed="true"> + <xs:sequence> + <xs:element name="charParams" minOccurs="0" maxOccurs="unbounded" type="tns:CharParamsType"/> + </xs:sequence> + </xs:complexType> + </xs:element> + </xs:sequence> + <xs:attribute name="wordFromDictionary" type="xs:boolean" use="optional"/> + <xs:attribute name="wordNormal" type="xs:boolean" use="optional"/> + <xs:attribute name="wordNumeric" type="xs:boolean" use="optional"/> + <xs:attribute name="wordIdentifier" type="xs:boolean" use="optional"/> + <xs:attribute name="wordPenalty" type="xs:integer" use="optional"/> + <xs:attribute name="meanStrokeWidth" type="xs:integer" use="optional"/> + </xs:complexType> + + <xs:complexType name="CharRecognitionVariant" mixed="true"> + <xs:attribute name="charConfidence" type="xs:integer" use="optional"/> + <xs:attribute name="serifProbability" type="xs:integer" use="optional"/> + </xs:complexType> + + <xs:complexType name="CharParamsType" mixed="true"> + <xs:sequence> + <xs:element name="charRecVariants" minOccurs="0"> + <xs:complexType> + <xs:sequence> + <xs:element name="charRecVariant" minOccurs="0" maxOccurs="unbounded" type="tns:CharRecognitionVariant"/> + </xs:sequence> + </xs:complexType> + </xs:element> + </xs:sequence> + <xs:attribute name="l" type="xs:integer" use="required"/> + <xs:attribute name="t" type="xs:integer" use="required"/> + <xs:attribute name="r" type="xs:integer" use="required"/> + <xs:attribute name="b" type="xs:integer" use="required"/> + <xs:attribute name="suspicious" type="xs:boolean" use="optional" default="false"/> + <xs:attribute name="proofed" type="xs:boolean" use="optional" default="false"/> + <xs:attribute name="wordStart" type="xs:boolean" use="optional"/> + <xs:attribute name="wordFromDictionary" type="xs:boolean" use="optional"/> + <xs:attribute name="wordNormal" type="xs:boolean" use="optional"/> + <xs:attribute name="wordNumeric" type="xs:boolean" use="optional"/> + <xs:attribute name="wordIdentifier" type="xs:boolean" use="optional"/> + <xs:attribute name="charConfidence" type="xs:integer" use="optional"/> + <xs:attribute name="serifProbability" type="xs:integer" use="optional"/> + <xs:attribute name="wordPenalty" type="xs:integer" use="optional"/> + <xs:attribute name="meanStrokeWidth" type="xs:integer" use="optional"/> + <xs:attribute name="characterHeight" type="xs:integer" use="optional"/> + <xs:attribute name="hasUncertainHeight" type="xs:boolean" use="optional"/> + <xs:attribute name="baseLine" type="xs:integer" use="optional"/> + </xs:complexType> + + <xs:simpleType name="TableCellBorderType"> + <xs:restriction base="xs:string"> + <xs:enumeration value="Absent"/> + <xs:enumeration value="Unknown"/> + <xs:enumeration value="White"/> + <xs:enumeration value="Black"/> + </xs:restriction> + </xs:simpleType> + + +</xs:schema> -- 1.5.6.5

1 0