<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
<html>
<head>
<link rel=stylesheet href="zinnia.css" media=all>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<title>Zinnia: Online hand writing recognition system with machine learning</title>
</head>
<body>
<h1>Zinnia: Online hand recognition system with machine learning</h1>
<p><a href="index-ja.html">[Japanese]</a><a href="index.html">[English]</a></p>
<p>
Zinnia is a simple, customizable and portable online hand recognition system
based on Support Vector Machines. Zinnia simply receives user pen strokes
as a sequence of coordinate data and outputs n-best characters sorted by
SVM confidence. To keep portability, Zinnia doesn't have any rendering
functionality. In addition to recognition, Zinnia provides training
module that allows us to create any hand-written recognition systems with low-cost.
</p>
<h2>Features</h2>
<ul>
<li>Practical accuracy with support vector machines
<li>Portable and compact design -- POSIX/Windows (depending on C++/STL)
<li>Thread-safe C/C++/Perl/Ruby/Python libraries
<li>Practical recognition speed (50--100char / sec)
<li>Fast training
</ul>
<h2>Download</h2>
<ul>
<li><b>Zinnia</b> is free software; you can redistribute it
and/or modify it under the terms of the <a
href="http://www.opensource.org/licenses/bsd-license.php">new BSD
License</a></li>
<li><b>Zinnia</b> main program
<h3><a name="source">Source</a></h3>
<ul>
<li>zinnia-0.02.tar.gz:<a href="src">download</a>
<li>No recognition models are included.
</ul>
<h3><a name="win">Binary package for MS-Windows</a></h3>
<ul>
<li>zinnia-0.02.zip:<a href="src">Download</a>
</ul>
<li><b>Zinnia</b> Recognition models
<h3>Zinnia-Tomoe</h3>
<ul>
<li>Model files trained with Tomoe data: <a href="src">download</a></li>
<li>Licence of Zinnia-tomoe is the same as that of Tomoe</li>
</ul>
</ul>
<h2>Install</h2>
<h3>UNIX</a></h3>
<pre>
% tar zxfv zinnia-X.X.tar.gz
% cd zinnia-X.X
% ./configure
% make
% su
# make install
</pre>
</li>
<p>Install recognition models</p>
<pre>
% tar zxfv zinnia-tomoe-XXXX.tar.gz
% zinnia-tomoe-XXXX
% ./configure
% make
% su
# make install
</pre>
<h3>Windows</h3>
<p>DLL and executable are included in zip file.
No recognition models are included. Run the following command after
putting model files in zip archived directory.
<pre>
bin\zinnia_convert.exe handwriting-ja.model.txt handwriting-ja.model
bin\zinnia_convert.exe handwriting-zh_CN.model.txt handwriting-zh_CN.model
</pre>
<h2>Usage (Recognition)</h2>
<p>Zinnia provides C/C++ libraries. Perl/Ruby/Python
libraries are also available with SWIG </p>
<h3>Sample code with C</h3>
<pre>
#include <stdio.h>
#include "zinnia.h"
int main(int argc, char **argv) {
size_t i;
zinnia_recognizer_t *recognizer;
zinnia_character_t *character;
zinnia_result_t *result;
recognizer = zinnia_recognizer_new();
if (!zinnia_recognizer_open(recognizer, "/usr/local/lib/zinnia/model/tomoe/handwriting-ja.model")) {
fprintf(stderr, "ERROR: %s\n", zinnia_recognizer_strerror(recognizer));
return -1;
}
zinnia_character_t *character = zinnia_character_new();
zinnia_character_clear(character);
zinnia_character_set_width(character, 300);
zinnia_character_set_height(character, 300);
zinnia_character_add(character, 0, 51, 29);
zinnia_character_add(character, 0, 117, 41);
zinnia_character_add(character, 1, 99, 65);
zinnia_character_add(character, 1, 219, 77);
zinnia_character_add(character, 2, 27, 131);
zinnia_character_add(character, 2, 261, 131);
zinnia_character_add(character, 3, 129, 17);
zinnia_character_add(character, 3, 57, 203);
zinnia_character_add(character, 4, 111, 71);
zinnia_character_add(character, 4, 219, 173);
zinnia_character_add(character, 5, 81, 161);
zinnia_character_add(character, 5, 93, 281);
zinnia_character_add(character, 6, 99, 167);
zinnia_character_add(character, 6, 207, 167);
zinnia_character_add(character, 6, 189, 245);
zinnia_character_add(character, 7, 99, 227);
zinnia_character_add(character, 7, 189, 227);
zinnia_character_add(character, 8, 111, 257);
zinnia_character_add(character, 8, 189, 245);
result = zinnia_recognizer_classify(recognizer, character, 10);
if (result == NULL) {
fprintf(stderr, "%s\n", zinnia_recognizer_strerror(recognizer));
return -1;
}
for (i = 0; i < zinnia_result_size(result); ++i) {
fprintf(stdout, "%s\t%f\n",
zinnia_result_value(result, i),
zinnia_result_score(result, i));
}
zinnia_result_destroy(result);
zinnia_character_destroy(character);
zinnia_recognizer_destroy(recognizer);
return 0;
}
</pre>
</p>
<pre>
% gcc example.c -lzinnia -o zinnia_sample
% ./zinnia_sample
</pre>
<h3>Comment</h3>
<ul>
<li>create recognizer
<li>load model file
<li>create character object
<li>clear character
<li>set canvas size
<li>specify stroke data (number of stroke, x-axis, y-axis)
<li>do recognition. result object is created. The last arg means the maximum size of characters requested
<li>print recognized character with score. results are sorted by score
<li>delete result object
<li>delete character object
<li>delete recognizer object
</ul>
<h3>Sample code with C++</h3>
<pre>
#include <iostream>
#include "zinnia.h"
int main(int argc, char **argv) {
zinnia::Recognizer *recognizer = zinnia::Recognizer::create();
if (!recognizer->open("/usr/local/lib/zinnia/model/tomoe/handwriting-ja.model")) {
std::cerr << recognizer->what() << std::endl;
return -1;
}
zinnia::Character *character = zinnia::Character::create();
character->clear();
character->set_width(300);
character->set_height(300);
character->add(0, 51, 29);
character->add(0, 117, 41);
character->add(1, 99, 65);
character->add(1, 219, 77);
character->add(2, 27, 131);
character->add(2, 261, 131);
character->add(3, 129, 17);
character->add(3, 57, 203);
character->add(4, 111, 71);
character->add(4, 219, 173);
character->add(5, 81, 161);
character->add(5, 93, 281);
character->add(6, 99, 167);
character->add(6, 207, 167);
character->add(6, 189, 245);
character->add(7, 99, 227);
character->add(7, 189, 227);
character->add(8, 111, 257);
character->add(8, 189, 245);
zinnia::Result *result = recognizer->classify(*character, 10);
if (!result) {
std::cerr << recognizer->what() << std::endl;
return -1;
}
for (size_t i = 0; i < result->size(); ++i) {
std::cout << result->value(i) << "\t" << result->score(i) << std::endl;
}
delete result;
delete character;
delete recognizer;
return 0;
}
</pre>
<h3>Sexp representation for character</h3>
<p>Character class (zinnia_character_t / zinnia::Character) has method
for an Sexp-based serialization.</p>
<pre>
(character
(width canvas width)
(height canvas height)
(strokes
((0-th-stroke 0-th-strokey) ... (0-th-stroke 0-th-strokey))
((1-th-stroke 0-th-strokey) ... (1-th-stroke 1-th-strokey))
((2-th-stroke 2-th-strokey) ... (2-th-stroke 2-th-strokey))
...))
</pre>
<p>Example</p>
<pre>
static const char sexp[] = "(character (width 1000)(height 1000)(strokes ((243 273)(393 450))((700 253)(343 486)(280 716)(393 866)(710 880))))";
zinnia_character_t *character = zinnia_character_new();
zinnia_character_parse(character, sexp);
</pre>
<pre>
static const char sexp[] = "(character (width 1000)(height 1000)(strokes ((243 273)(393 450))((700 253)(343 486)(280 716)(393 866)(710 880))))";
zinnia::Character *character = zinnia::Character::create();
character->parse(sexp);
</pre>
<h2>Training</h2>
<p>
In order to make a training with Zinnia, you need to make a golden
(training) data. Training data is written in S-expression.
Generally speaking, more data yields better quality. Zinnia only supports
batch training so far.</p>
<p>Example</p>
<pre>
(character (value あ) (width 300) (height 300) (strokes ((54 58)(249 68)) ((147 10)(145 201)(182 252)) ((224 103)(149 230)(82 240)(53 204)(86 149)(182 139)(240 172)(248 224)(228 250))))
(character (value い) (width 300) (height 300) (strokes ((56 63)(43 213)(67 259)(94 243)) ((213 66)(231 171)(208 217))))
(character (value う) (width 300) (height 300) (strokes ((102 35)(187 45)) ((73 121)(167 105)(206 139)(198 211)(135 275))))
(character (value え) (width 300) (height 300) (strokes ((140 19)(162 38)) ((62 105)(208 100)(51 263)(128 205)(188 268)(260 252))))
(character (value お) (width 300) (height 300) (strokes ((64 94)(240 98)) ((148 35)(159 129)(140 199)(105 247)(64 228)(101 161)(192 161)(222 223)(189 257)) ((223 49)(253 89))))
</pre>
</p>
<p>You might want to look into *.s file in zinnia-tomoe as references</p>
<p>Use zinnia_learn to conduct training</p>
<pre>
% zinnia_learn train-file model-file
...
learning: (8/3033) 8 ....
learning: (9/3033) 9 ...
learning: (10/3033) 々 ............
learning: (11/3033) 〆 ....
learning: (12/3033) あ ....
learning: (13/3033) い .......
learning: (14/3033) う ...............
learning: (15/3033) え ......................................................................................
learning: (16/3033) お ......
learning: (17/3033) か .......
learning: (18/3033) き .......
learning: (19/3033) く .......
</pre>
<p>train-file is a training data and model-file is a model file
zinnia_learn generates</p>
<p>use zinnia command for testing</p>
<pre>
% zinnia -m model-file < test-file
</pre>
<p>model-file is a file zinnia_learn generates. text-file is a test data
written in Sexp format.</p>
<p>Once training completes successfully, model-file.txt (text file)
and model-file (binary file) will be generated.
text-model is an architecture-independent format, and model-file is
an architecture-dependent binary model. Zinnia recognizer can only load
binary model. zinnia_convert program converts text-model
into binary model.</p>
<pre>
% zinnia_convert model-file.txt model-file
</pre>
<p>In addition, text-model can be converted into C-header file.</p>
<pre>
% zinnia_convert --name=my_model --make_header model-file.txt my_model.h
</pre>
<p>In order to use a header file, include my_model.h in C/C++ source
file and load the data using zinnia_recognizer_open_from_ptr().
my_model(content of mode) and my_model_size(model size) is defined in
the header file.
</p>
<pre>
#include "my_model.h"
if (!zinnia_recognizer_open_from_ptr(recognizer, my_model, my_model_size)) {
/* error */
}
</pre>
<h2>Model compression</h2>
<p>By omitting features having small score, model can be compressed with
scarifying recognition accuracy.
<pre>
% zinnia_convert -c 0.01 model-file.txt model1
% zinnia_convert -c 0.001 model-file.txt model2
% ls -h -l model*
-rw-r--r-- 1 taku taku 3.1M 2008-07-14 12:50 model1
-rw-r--r-- 1 taku taku 25M 2008-07-14 12:50 model2
</pre>
<p>c is a threshold. Default setting 0.001.
Larger threshold gives more aggressive compression.</p>
<h2>API list</h2>
<ul>
<li><a href="doxygen/annotated.html">C++ API</a>
<li><a href="doxygen/zinnia_8h.html">C API functions</a>
</ul>
<p>
</p>
</body>
</html>
distrib
>
Mandriva
>
2010.0
>
i586
>
media
>
contrib-release
>
by-pkgid
>
98907970f64a86270044fe1268c8e69d
>
files
>
35
