wandoc |_(filters?, | |_(filter+) | |_(inputs+, | | |_(input+, | | | |_(#PCDATA) | | | | | |__wanda_link*) ... | | | |__module+, | | |_(#PCDATA) | | | |__outputs+, | | |_(output+, | | | |_(features?) | | | |_(feature+) | | | |_(#PCDATA) | | | | | | | | | | | |__wanda_link*) ... | | | |__wanda_link*) ... | | |__annotations?, | |_(annotation+) | |_(comment?, | | |_(#PCDATA) | | | |__wanda_link*) ... | | |__pages?, | |_(page+) | |_(filters?, ... | |__annotations?, ... | |__regions?, | | |_(region+) | | |_(filters?, ... | | |__annotations?, ... | | |__points+, | | | |_(point+) | | | |_EMPTY | | | | | | | | |__regions?, ... | | |__wanda_link*) ... | | | | | |__wanda_link*, ... | |__meta?) ... | | |__wanda_link*, | |_EMPTY | |__meta?) |_EMPTY
<?xml version="1.0" encoding="UTF-8"?> <!--Sample XML file generated by XMLSPY v5 rel. 3 U (http://www.xmlspy.com)--> <!DOCTYPE wandoc SYSTEM "wandoc_.dtd"> <wandoc id="20032004_0001" label="WANDA test and development sample" xmlns="http://pentel.ipk.fhg.de/wandaXML/wandoc/wandoc.dtd"> <pages number_of="1"> <page id="20032004_0001_copy51" label="frontpage" next=""> <filters number_of="1"> <filter type="import" label="ibisScan" > <inputs> <input type="stream" number="1" xmlns="../scan.dtd"> <scan/> </input> </inputs> <module type="extern" exec="ibis.exe"> <meta version="3.51"/> </module> <outputs> <output type="file"> <wanda_link href="docServer://wanda/database/.../0001.tif"/> </output> </outputs> </filter> </filters> <annotations number_of="3"> <annotation type="content" xmlns="../content.dtd"> <whole_document type="envelope" intent="personal"/> </annotation> <annotation type="writer" xmlns="../writer.dtd"> <writer id="2015"> <person> <name firstname="Altug" surname="Metin"/> <gender type="male"/> <born year="1978"/> </person> <properties handedness="left" skill="ok"/> <education country="France" level="high"/> <language native="French"/> <meta author="SIC Writer" email="sic@here.we.are" institution="Fraunhofer IPK" version="1.0" created="2003-03-17" /> </writer> </annotation> <annotation type="material" xmlns="../material.dtd"> <material> <paper type="writing" size="less_A6" material="woodfree" weight="less_60" product="IBM_copy_paper" absorbency="low"/> <pad type="paper" surface="even" hardness="soft"/> </material> </annotation> </annotations> <regions number_of="1"> <region id="20032004_0001_copy51_0001_213746432" label="Hello...happy with it." next=""> <points> <point x="0" y="0"/> <point x="10" y="0"/> <point x="0" y="10"/> <point x="10" y="10"/> </points> <annotations number_of="3"> <annotation type="material" xmlns="../material.dtd"> <material> <pen type="fountain_pen" product="waterman_serenite"> <tip type="metal_nib" material="gold" diameter="medium" flexibility="high"/> <ink viscosity="low" transparence="opaque" color="gray" product="waterman"/> </pen> </material> </annotation> <annotation type="script" xmlns="../script.dtd"> <script type="latin" language="english"> <style major="cursive" connection="arced" caps="lower_upper" consistency="high" stroke_quality="disturbed" embellishment="simplified" stroke_quality_causes="ink_aging" inter-word_connectivity="low" intra-word_connectivity="high" relative_writing_speed="faster"/> </script> </annotation> <annotation type="content" xmsl="../content.dtd"> <content> <text_block type="addressee_address_block" length="paragraph" > <properties tone="neutral" grammar="ok" spelling="bad"/> <verbatim> Alfred Joe 223 daoun the rode The Bled USA </verbatim> </text_block> </content> </annotation> </annotations> <filters number_of="1"> <filter type="feature_extract" label="nicifeat"> <inputs> <input type="stream" number="1" xmlns="../nicifeat.dtd"> <nicifeat/> </input> </inputs> <module type="client" exec="nicifeatmeasurement"/> <outputs> <output type="stream"> <features number_of="4"> <!-- We do not need to precise the name space because the feature tag is a generic wandoc tag --> <feature name="first" type="decimal" unit="pixel" value="1.0"/> <feature name="second" type="decimal" unit="pixel" value="2.0"/> <feature name="third" type="decimal" unit="pixel" value="3.0"/> <feature name="fourth" type="decimal" unit="pixel" value="4.0"/> </features> </output> </outputs> </filter> </filters> </region> </regions> </page> </pages> </wandoc>
<!-- =========================================================== wandoc (Wanda DOCUMENT Modeling Language) author: Katrin Fanke, Lambert Schomaker, Isabelle Guyon institution: Fraunhofer IPK, Rijksuniversiteit Groningen, Clopinet version: 2.0 created: 2002-04-11-00-00 modified: 2003-05-08-00-00 =========================================================== --> <!ENTITY % anno_types " * | document | writer | script | material | content "> <!ENTITY % filter_types " * | import | processing | feature_extract "> <!ENTITY % input_types " * | stream | file | var "> <!ENTITY % module_types " * | client | server | extern "> <!ENTITY % output_types " * | stream | file | var "> <!ENTITY % feature_types " * | boolean | decimal "> <!-- ======================================================= --> <!ELEMENT wandoc (filters?, annotations?, pages? , wanda_link*, meta?)> <!ATTLIST wandoc id CDATA #REQUIRED label CDATA "Enter label !" xmlns CDATA #IMPLIED > <!-- ======================================================= --> <!ELEMENT pages (page+)> <!ATTLIST pages number_of CDATA #IMPLIED > <!ELEMENT page (filters?, annotations?, regions?, wanda_link*, meta?)> <!ATTLIST page id CDATA #REQUIRED label CDATA #IMPLIED next CDATA #IMPLIED > <!-- ======================================================= --> <!ELEMENT regions (region+)> <!ATTLIST regions number_of CDATA #IMPLIED > <!ELEMENT region (filters?, annotations?, points+, regions?, wanda_link*)> <!ATTLIST region id CDATA #REQUIRED label CDATA #IMPLIED next CDATA #IMPLIED > <!-- ======================================================= --> <!ELEMENT annotations (annotation+)> <!ATTLIST annotations number_of CDATA #IMPLIED > <!ELEMENT annotation (comment?, wanda_link*)> <!ATTLIST annotation type (%anno_types;) #IMPLIED xmlns CDATA #IMPLIED > <!ELEMENT comment (#PCDATA)> <!-- ======================================================= --> <!ELEMENT filters (filter+)> <!ATTLIST filters number_of CDATA #IMPLIED > <!ELEMENT filter (inputs+, module+, outputs+, wanda_link*)> <!ATTLIST filter type (%filter_types;) #IMPLIED label CDATA #IMPLIED xmlns CDATA #IMPLIED > <!ELEMENT inputs (input+, wanda_link*)> <!ATTLIST inputs number_of CDATA #IMPLIED > <!ELEMENT input (#PCDATA)> <!--type and the n-th input for the module --> <!ATTLIST input type (%input_types;) #REQUIRED number CDATA #IMPLIED label CDATA #IMPLIED xmlns CDATA #IMPLIED > <!ELEMENT module (#PCDATA)> <!ATTLIST module type (%module_types;) #REQUIRED exec CDATA #REQUIRED > <!ELEMENT outputs (output+, wanda_link*)> <!ATTLIST outputs number_of CDATA #IMPLIED > <!ELEMENT output (features?)> <!ATTLIST output type (%output_types;) #REQUIRED number CDATA #IMPLIED label CDATA #IMPLIED xmlns CDATA #IMPLIED > <!-- ======================================================= --> <!ELEMENT features (feature+)> <!ATTLIST features number_of CDATA #IMPLIED > <!ELEMENT feature (#PCDATA)> <!ATTLIST feature name CDATA #REQUIRED type (%feature_types;) #IMPLIED unit CDATA #IMPLIED value CDATA #REQUIRED number CDATA #IMPLIED > <!-- ====================================================== --> <!ELEMENT points (point+)> <!ELEMENT point EMPTY> <!ATTLIST point x CDATA #REQUIRED y CDATA #REQUIRED > <!-- ======================================================= --> <!ELEMENT wanda_link EMPTY> <!ATTLIST wanda_link href CDATA #REQUIRED > <!-- This is a proposition of definition of wanda_link as xlink: <!ATTLIST wanda_link xmlns:xlink CDATA #FIXED "http://www.w3.org/1999/xlink" xlink:type (simple) #FIXED "simple" xlink:href CDATA #REQUIRED xlink:show (embed) #FIXED "embed" xlink:actuate (onLoad) #FIXED "onLoad" > We made a fix choice for the xlink behavior that will carry over for the entire wandoc document. If attribute show is set to embed then the xlink replaces the element link. When attribute actuate is set to onLoad, replacement is immediate (similarly to well-known element <html:img src=... >). For other options see: http://www.zvon.org/xxl/xlink/OutputExamples/frame_xlinksimple_html.html or http://www.w3.org/TR/REC-xml-names/ --> <!-- ======================================================= --> <!ELEMENT meta EMPTY> <!ATTLIST meta author CDATA #IMPLIED email CDATA #IMPLIED institution CDATA #IMPLIED version CDATA #IMPLIED created CDATA #IMPLIED modified CDATA #IMPLIED >
The writer description is part of the Wanda XML language.
It records information on the writer that may be relevant to the writer
identification process from sample handwriting. It excludes other personal
information. Therefore, only year of birth, education, gender, and
language information are considered.
CDATA
</annotation>
Description: Tag enclosing a user-defined annotation (an application specific DTD is required).
See, for instance, the
following annotation DTDs: writer ,
script ,
material ,
content .
Parent Element(s):
<annotations/> -- Container of annotations.
CDATA
>
</annotations>
Description: Container of annotations.
Parent Element(s):
</comment>
Description: Free text comment.
Parent Element(s):
<annotation/> -- Tag enclosing a user-defined annotation.
CDATA
CDATA
CDATA
CDATA
</feature>
Description: Tag to record a statistic about the document, e.g. average ascender length.
Parent Element(s):
<features/> -- Container of features.
CDATA
>
</features>
Description: Container of features.
Parent Element(s):
<output/> -- Tag enclosing user-defined outputs.
CDATA
CDATA
</filter>
Description: Generic filter definition (a function/plugin call).
Parent Element(s):
<filters/> -- Container of fiters.
CDATA
>
</filters>
Description: Container of filters.
Parent Element(s):
CDATA
CDATA
CDATA
</input>
Description: Tag enclosing user-defined inputs (an application specific DTD is required).
See for instance the NICI measurement filter DTD: nicifeat .
Parent Element(s):
<inputs/> -- Container of inputs.
CDATA
>
</inputs>
Description: Container of inputs.
Parent Element(s):
<filter/> -- Generic filter definition.
CDATA
CDATA
CDATA
CDATA
CDATA
CDATA
/>
Description: Information about how the document annotations were generated.
Parent Element(s):
CDATA
</module>
Description: Executable module (function/plugin call).
Parent Element(s):
<filter/> -- Generic filter definition.
CDATA
CDATA
CDATA
</output>
Description: Tag enclosing user-defined outputs (an application specific DTD is required).
See for instance the NICI measurement filter DTD: nicifeat .
Parent Element(s):
<outputs/> -- Container of outputs.
CDATA
>
</outputs>
Description: Container of outputs.
Parent Element(s):
<filter/> -- Generic filter definition.
CDATA
CDATA
CDATA
</page>
Description: Document page containing a single image and annotations.
Parent Element(s):
<pages/> -- Container of pages.
CDATA
>
</pages>
Description: Container of pages.
Parent Element(s):
<wandoc/> -- Root element of a Wanda document annotation.
CDATA
CDATA
/>
Description: Cartesian coordinate point, in pixel units on the image.
Parent Element(s):
<points/> -- Container of points.
</points>
Description: Container of points.
Parent Element(s):
<region/> -- Region of interest defined by a polygon or rectangle and annotated.
CDATA
CDATA
CDATA
</region>
Description: Region of interest.
Parent Element(s):
<regions/> -- Container of regions.
CDATA
>
</regions>
Description: Container of regions.
Parent Element(s):
CDATA
/>
Description: Element that will be replaced by the file it points to.
Parent Element(s):
CDATA
CDATA
CDATA
</wandoc>
Description: Root element of a Wanda document annotation.
Parent Element(s):
None
WRITER DTD
writer DTD Tree
writer
|_(person,
| |_(name,
| | |_EMPTY
| |
| |__gender,
| | |_EMPTY
| |
| |__born)
| |_EMPTY
|
|
|__properties?,
| |_EMPTY
|
|__education?,
| |_EMPTY
|
|__language?,
| |_EMPTY
|
|__meta?)
|_EMPTY
writer XML example
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE writer SYSTEM "writer_.dtd">
<writer id="2015">
<person>
<name firstname="Altug" surname="Metin"/>
<gender type="male"/>
<born year="1978"/>
</person>
<properties handedness="left" skill="ok"/>
<education country="France" level="high"/>
<language native="French"/>
<meta author="SIC Writer"
institution="Fraunhofer IPK"
version="1.0"
created="2003-03-17"
modified=""/>
</writer>
writer DTD File
<!-- edited with XMLSPY v5 rel. 3 U (http://www.xmlspy.com)
by Isabelle Guyon (Clopinet) -->
<!-- ===========================================================
writer (Wanda WRITER Modeling Language)
author: Altug Metin, edited by Isabelle Guyon
institution: Fraunhofer IPK, Clopinet
version: 3.0
created: 2002-02-18-00-00
modified: 2003-05-08-00-00
=========================================================== -->
<!ENTITY % gender_types " * | female | male ">
<!ENTITY % handedness_types " * | left | right ">
<!ENTITY % skill_types " * | bad | ok | good ">
<!ENTITY % education_level_types
" * | elementary | medium | high ">
<!ENTITY % education_country_types " * |
albania |
alberta |
ashmore |
algeria |
afghanistan |
argentina |
anguilla |
armenia |
azerbaijan |
alaska |
alabama |
anguilla |
andorra |
angola |
antigua_barbuda |
arkansas |
american_samoa |
australia |
austria |
aruba |
antarctica |
arizona |
bahrain |
barbados |
british_columbia |
burundi |
belgium |
bahamas |
bangladesh |
belize |
brazil |
bermuda |
bosnia_hercegovina |
bolivia |
burma |
botswana |
bhutan |
bulgaria |
bouvet_island |
belarus |
byelorussia |
brunei |
california |
cambodia |
china |
chad |
sri_lanka |
congo |
croatia |
cayman_islands |
colombia |
chile |
cameroon |
canada |
colorado |
comoros |
costa_rica |
czech_republic|
slovakia |
connecticut |
cuba |
cape_verde |
cook_islands |
central_african_republic |
cyprus |
district_of_columbia |
delaware |
denmark |
benin |
dominica |
dominican_republic |
eritrea |
ecuador |
equatorial_guinea |
easttimor |
england |
estonia |
elsalvador |
ethiopia |
faroe_islands |
french_guiana |
finland |
fiji |
falkland_islands |
florida |
micronesia |
french_polynesia |
france |
djibouti |
georgia |
kiribati |
grenada |
germany |
ghana |
gibraltar |
greenland |
gambia |
gabon |
guadeloupe |
greece |
georgia |
guatemala |
guam |
guinea |
guyana |
hawaii |
hongkong |
honduras |
haiti |
hungary |
iowa |
iceland |
idaho |
ireland |
india |
illinois |
indiana |
indonesia |
iraq |
iran |
israel |
italy |
cote_d_ivoire |
japan |
johnston_atoll |
jamaica |
jan_mayen |
jordan |
kenya |
kyrgyzstan |
kirghiz |
north_korea |
south_korea |
kansas |
kuwait |
kentucky |
kazakhstan |
louisiana |
liberia |
lebanon |
liechtenstein |
lithuania |
lesotho |
laos |
luxembourg |
latvia |
libya |
massachusetts |
manitoba |
monaco |
maryland |
maine |
mauritius |
madagascar |
macao |
michigan |
montserrat |
oman |
mali |
malta |
minnesota |
missouri |
mongolia |
martinique |
morocco |
mississippi |
montana |
mauritania |
moldova |
moldavia |
malawi |
mexico |
malaysia |
mozambique |
netherlands_antilles |
nebraska |
north_carolina |
north_dakota |
netherlands |
newfoundland_labrador |
niger |
new_hampshire |
northern_ireland |
new_jersey |
new_brunswick |
new_caledonia |
northern_mariana_islands |
new_mexico |
vanuatu |
norway |
nepal |
nicaragua |
nigeria |
nova_scotia |
northwest_territories |
nauru |
nunavut |
nevada |
northern_mariana_islands |
norfolk_island |
new_york_state |
new_zealand |
ohio |
oklahoma |
ontario |
oregon |
mayotte |
pennsylvania |
pitcairn_island |
peru |
paracel_islands |
guinea_bissau |
philippines |
prince_edward_island |
pakistan |
poland |
panama |
portugal |
papua_new_guinea |
puerto_rico |
portuguese_timor |
palau |
paraguay |
qatar |
quebec_province |
reunion |
zimbabwe |
rhode_island |
romania |
russia |
rwanda |
ryukyu_islands_southern |
south_africa |
svalbard |
south_carolina |
south_dakota |
seychelles |
sao_tome_and_principe |
senegal |
spanish_north_africa |
singapore |
sudan |
sikkim |
sierra_leone |
san_marino |
saskatchewan |
somalia |
spain |
swaziland |
surinam |
western_sahara |
scotland |
saudi_arabia |
swan_islands |
sweden |
namibia |
syria |
switzerland |
tajikistan |
togo |
thailand |
tunisia |
turkmenistan |
tokelau |
tennessee |
tonga |
trinidad_and_tobago |
united_arab_emirates |
turkey |
tuvalu |
texas |
tanzania |
egypt |
united_states_caribbean_islands |
uganda |
unitedkingdom |
ukraine |
united_states_pacific_islands |
soviet_union |
united_states |
utah |
burkina_faso |
uruguay |
uzbekistan |
virginia |
british_virgin_islands |
vaticancity |
venezuela |
united_states_virgin_islands |
vietnam |
vermont |
washington_state |
wallis_and_futuna |
wisconsin |
wake_island |
wales |
samoa |
west_virginia |
wyoming |
christmas_island |
cocos_keeling_islands |
maldives |
saint_kitts-nevis |
marshall_islands |
midway_islands |
niue |
saint_kitts-nevis-anguilla |
saint_helena |
saint_lucia |
saint_pierre_and_miquelon |
saint_vincent_and_the_grenadines |
macedonia |
slovakia |
spratly_island |
czech_republic |
south_georgia |
slovenia |
canada |
united_kingdom |
yemen |
yukon_territory |
yemen |
yugoslavia |
zambia ">
<!-- source: http://www.loc.gov/marc/countries/ -->
<!ENTITY % native_language_types " * |
afrikaans |
akkadian |
albanian |
arabic |
armenian |
assyrian |
aymara |
malay |
bangala |
basque |
bavarian |
belorusian |
bengali |
berber_tamazight |
breton |
bulgarian |
burmese |
cambodian |
cantonese |
catalan |
cherokee_tsalagi |
croatian |
czech |
dakota |
danish |
dauphinois |
dutch |
egyptian |
english |
estonian |
finnish |
flemish |
french |
frisian |
fukienese |
gaelic |
galician |
georgian |
german |
greek |
guarani |
gujarati |
hakka |
halaka |
hausa |
hawaiian |
hebrew |
hundustani_hindi |
hungarian |
icelandic |
indonesian |
italian |
japanese |
javanese |
kamilaroi |
korean |
kurdish |
ladino |
latvian |
lithuanian |
lojban |
luganda |
macedonian |
malayalam |
maltese |
mandarin_chinese |
manx |
maori |
mohawk |
mon |
mongolian |
myanmar |
navajo |
nepalese |
norwegian |
occitan |
ojibwe |
oneida |
papiamentu |
persian |
pidgin |
pitcairn |
polish |
portuguese |
punjabi |
quechua |
rasta |
romanian |
romansch |
romany |
russian |
sardinian |
scots |
serbian |
sinhalese |
slovak |
slovenian |
spanish |
sranan |
sudanese |
swabian |
swahili |
swedish |
tagalog |
tamil |
telugu |
thai |
tlingit |
turkish |
ukranian |
viennese |
vietnamese |
welsh |
wu |
yiddish ">
<!-- source: http://www.tesarta.com/www/resources/languages.html -->
<!-- ======================================================= -->
<!ELEMENT writer
(person, properties?, education?, language?, meta?)>
<!-- root tag -->
<!ATTLIST writer
id CDATA #REQUIRED
>
<!-- ======================================================= -->
<!-- every writer is a person ... -->
<!ELEMENT person (name, gender, born)>
<!-- person's name -->
<!ELEMENT name EMPTY>
<!ATTLIST name
firstname CDATA #IMPLIED
surname CDATA #IMPLIED
>
<!ELEMENT gender EMPTY>
<!-- person's gender -->
<!ATTLIST gender
type (%gender_types;) "*"
>
<!ELEMENT born EMPTY>
<!-- person's birth -->
<!ATTLIST born
year CDATA "*"
>
<!-- ======================================================= -->
<!ELEMENT properties EMPTY>
<!-- writer properties -->
<!ATTLIST properties
handedness (%handedness_types;) "*"
skill (%skill_types;) "*"
>
<!-- ======================================================= -->
<!ELEMENT education EMPTY>
<!-- writer's (handwrting) education -->
<!ATTLIST education
country (%education_country_types;) "*"
level (%education_level_types;) "*"
>
<!-- ======================================================= -->
<!ELEMENT language EMPTY>
<!ATTLIST language
native (%native_language_types;) "*"
>
<!-- ======================================================= -->
<!ELEMENT meta EMPTY>
<!-- author of the writer info and location of writer
info's entering/storage -->
<!ATTLIST meta
author CDATA #REQUIRED
institution CDATA #REQUIRED
version CDATA #REQUIRED
created CDATA #REQUIRED
modified CDATA #REQUIRED
>
writer XML tag reference
CDATA
/>
Description: Year born.
Parent Element(s):
<person/> -- Civil state information.
/>
Description: Education received that may affect handwriting.
Parent Element(s):
<writer/> -- Writer root element.
/>
Description: Male/female.
Parent Element(s):
<person/> -- Civil state information.
/>
Description: Language(s).
Parent Element(s):
<writer/> -- Writer root element.
CDATA
CDATA
CDATA
CDATA
CDATA
/>
Description: How this information was collected.
Parent Element(s):
<writer/> -- Writer root element.
CDATA
CDATA
/>
Description: Person name.
Parent Element(s):
<person/> -- Civil state information.
</person>
Description: Civil state information.
Parent Element(s):
<writer/> -- Writer root element.
/>
Description: Writing ability properties.
Parent Element(s):
<writer/> -- Writer root element.
CDATA
>
</writer>
Description: Writer root element.
Parent Element(s):
None
MATERIAL DTD
material DTD Tree
material
|_(paper?,
| |_EMPTY
|
|__pen?,
| |_(tip?,
| | |_EMPTY
| |
| |__ink)
| |_EMPTY
|
|
|__pad?,
| |_EMPTY
|
|__meta?)
|_EMPTY
material XML example
<?xml version="1.0" encoding="UTF-8"?>
<!--Sample XML file generated by XMLSPY v5 rel. 3 U
(http://www.xmlspy.com)-->
<!DOCTYPE material SYSTEM "material_.dtd">
<material>
<paper type="writing"
size="less_A6"
material="woodfree"
weight="less_60"
product="IBM_copy_paper"
absorbency="low"/>
<pen type="fountain_pen" product="waterman_serenite">
<tip type="metal_nib"
material="gold"
diameter="medium"
flexibility="high"/>
<ink viscosity="low"
transparence="opaque"
color="gray"
product="waterman"/>
</pen>
<pad type="paper" surface="even" hardness="soft"/>
</material>
material DTD File
<!-- ===========================================================
material (Wanda MATERIAL Modeling Language)
author: Katrin Fanke, Gerhard Grube, Lambert Schomaker,
Louis Vuurpijl, Isabelle Guyon
institution: Fraunhofer IPK, Landeskriminalamt Berlin,
Rijksuniversiteit Groningen, Nijmegen University,
Clopinet
version: 3.0
created: 2002-03-18-00-00
modified: 2003-05-08-00-00
=========================================================== -->
<!ENTITY % pen_type_types
" * | pencil | mechanical_pencil | propelling_pencil |
ball_point_pen | roller_ball_pen | gel_ink_pen |
porous_point_pen | fine_line_pen | fountain_pen |
steel_nib_pen | calligraphic_pen | quill">
<!ENTITY % tip_type_types
" * | pencil | ball_pen | metal_nib | plastic_nib |
flexible_plastic_nib | stiff_perforated_plastic_point |
fiber_tip | felt_tip | ceramic_tip ">
<!ENTITY % tip_material_types
" * | metal | plastic | ceramic | fibers | felt | gold | steel ">
<!ENTITY % tip_flexibility_types " * | low | normal | high ">
<!ENTITY % ink_viscosity_types " * | low | medium | high ">
<!ENTITY % ink_transparence_types
" * | opaque | semi_opaque | transparent ">
<!ENTITY % ink_color_types
" * | white | black | gray | purple | blue | green |
yellow | orange | red | others ">
<!ENTITY % paper_type_types
" * | writing | newspaper | concept | check | ledger |
flint_glazed | board | filter | embossed | creped | grained
| mottled | cast_coated | absorbent | bleached ">
<!ENTITY % paper_size_types
" * | less_A6 | A6 | A5 | US_letter | A4 | larger_than_A4 ">
<!ENTITY % paper_material_types " * | woodfree | rice ">
<!ENTITY % paper_weight_types
" * | less_60 | 60 | 70 | 80 | 90 | 100 | 110 | 120 |
more_than_120 ">
<!ENTITY % paper_absorbency_types " * | low | normal | height ">
<!ENTITY % pad_type_types
" * | electronic_tablet | paper | glass | wood | metal |
hard_pad | soft_pad ">
<!ENTITY % pad_hardness_types " * | soft | normal | hard ">
<!ENTITY % pad_surface_types " * | even | structured ">
<!-- ======================================================= -->
<!ELEMENT material (paper?, pen?, pad?, meta?)>
<!-- Paper specific information ============================ -->
<!ELEMENT paper EMPTY>
<!ATTLIST paper
type (%paper_type_types;) #IMPLIED
size (%paper_size_types;) #REQUIRED
material (%paper_material_types;) #IMPLIED
weight (%paper_weight_types;) #IMPLIED
product CDATA #IMPLIED
absorbency (%paper_absorbency_types;) #REQUIRED
>
<!-- Pen and Ink specific information ====================== -->
<!ELEMENT pen (tip?, ink)>
<!ATTLIST pen
type (%pen_type_types;) #REQUIRED
product CDATA #IMPLIED
>
<!ELEMENT tip EMPTY>
<!ATTLIST tip
type (%tip_type_types;) #IMPLIED
material (%tip_material_types;) #IMPLIED
diameter CDATA #IMPLIED
flexibility (%tip_flexibility_types;) #REQUIRED
>
<!ELEMENT ink EMPTY>
<!ATTLIST ink
viscosity (%ink_viscosity_types;) #REQUIRED
transparence (%ink_transparence_types;) #IMPLIED
color (%ink_color_types;) #REQUIRED
product CDATA #IMPLIED
>
<!-- Pad specific information ============================== -->
<!ELEMENT pad EMPTY>
<!ATTLIST pad
type (%pad_type_types;) #IMPLIED
hardness (%pad_hardness_types;) #REQUIRED
surface (%pad_surface_types;) #REQUIRED
>
<!-- ======================================================= -->
<!ELEMENT meta EMPTY>
<!ATTLIST meta
author CDATA #IMPLIED
email CDATA #IMPLIED
institution CDATA #IMPLIED
version CDATA #IMPLIED
created CDATA #IMPLIED
modified CDATA #IMPLIED
>
material XML tag reference
CDATA
/>
Description: Type and color of ink.
Parent Element(s):
<pen/> -- Writing pen.
</material>
Description: Material used for writing.
Parent Element(s):
None
CDATA
CDATA
CDATA
CDATA
CDATA
CDATA
/>
Description: How this information was collected.
Parent Element(s):
<material/> -- Material used for writing.
/>
Description: Writing support.
Parent Element(s):
<material/> -- Material used for writing.
CDATA
/>
Description: Writing paper.
Parent Element(s):
<material/> -- Material used for writing.
CDATA
</pen>
Description: Writing pen.
Parent Element(s):
<material/> -- Material used for writing.
CDATA
/>
Description: Pen tip.
Parent Element(s):
<pen/> -- Writing pen.
SCRIPT DTD
script DTD Tree
script
|_(style,
| |_EMPTY
|
|__meta?)
|_EMPTY
script XML example
<?xml version="1.0" encoding="UTF-8"?>
<!--Sample XML file generated by XMLSPY v5 rel. 3 U
(http://www.xmlspy.com)-->
<!DOCTYPE script SYSTEM "script_.dtd">
<script type="latin" language="afrikaans">
<style
major="cursive"
connection="arced"
caps="lower_upper"
consistency="high"
stroke_quality="disturbed"
embellishment="simplified"
stroke_quality_causes="ink_aging"
inter-word_connectivity="low"
intra-word_connectivity="high"
relative_writing_speed="faster"/>
</script>
script DTD File
<!-- ===========================================================
script (Wanda SCRIPT Modeling Language)
author: Katrin Fanke, Lambert Schomaker,
Gerhard Grube, Louis Vuurpijl, Isabelle Guyon
institution: Fraunhofer IPK, Rijksuniversiteit Groningen,
Landeskriminalamt Berlin, Nijmegen University, Clopinet
version: 3.0
created: 2002-03-18-00-00
modified: 2003-05-08-00-00
=========================================================== -->
<!-- source: Writing Systems of the World:
Alphabets, Syllabaries, Pictograms
by Nakanishi Akira and Akira Nakanishi -->
<!ENTITY % script_type_types
" * |
latin |
greek |
russian_cyrillic |
georgian |
armenian |
other_european |
hebrew |
arabic |
farsi |
urdu |
maldivian |
other_west_asiatic |
devanagari |
gurmukhi |
gujarati |
oriya |
bengali |
tamil |
telugu |
kannanda |
malayalam |
sinhalese |
other_indian |
burmese |
khmer |
thai |
lao |
other_southeast_asia |
chinese_hanzi |
tibetan |
mongolian |
korean_hangul |
japanese_kanji |
japanese_kana |
other_east_asia |
amharic |
other_african |
south_american |
other_american ">
<!-- source: http://www.tesarta.com/www/resources/languages.html -->
<!-- NOTE: The script language is different
from the native language of the writer. -->
<!ENTITY % language_types
"* |
afrikaans |
akkadian |
albanian |
arabic |
armenian |
assyrian |
aymara |
malay |
bangala |
basque |
bavarian |
belorusian |
bengali |
berber_tamazight |
breton |
bulgarian |
burmese |
cambodian |
cantonese |
catalan |
cherokee_tsalagi |
croatian |
czech |
dakota |
danish |
dauphinois |
dutch |
egyptian |
english |
estonian |
finnish |
flemish |
french |
frisian |
fukienese |
gaelic |
galician |
georgian |
german |
greek |
guarani |
gujarati |
hakka |
halaka |
hausa |
hawaiian |
hebrew |
hundustani_hindi |
hungarian |
icelandic |
indonesian |
italian |
japanese |
javanese |
kamilaroi |
korean |
kurdish |
ladino |
latvian |
lithuanian |
lojban |
luganda |
macedonian |
malayalam |
maltese |
mandarin_chinese |
manx |
maori |
mohawk |
mon |
mongolian |
myanmar |
navajo |
nepalese |
norwegian |
occitan |
ojibwe |
oneida |
papiamentu |
persian |
pidgin |
pitcairn |
polish |
portuguese |
punjabi |
quechua |
rasta |
romanian |
romansch |
romany |
russian |
sardinian |
scots |
serbian |
sinhalese |
slovak |
slovenian |
spanish |
sranan |
sudanese |
swabian |
swahili |
swedish |
tagalog |
tamil |
telugu |
thai |
tlingit |
turkish |
ukranian |
viennese |
vietnamese |
welsh |
wu |
yiddish ">
<!ENTITY % major_style_types
" * | cursive | mixed | handprint | blockprint ">
<!ENTITY % cap_type_types
" * | lower_upper | all_caps | lowercase | uppercase ">
<!ENTITY % connection_types
" * | arced | garland | angular | straight | indetermined ">
<!ENTITY % consistency_types
" * | high | normal | low ">
<!ENTITY % embellishment_types
" * | simplified | normal | enriched ">
<!ENTITY % stroke_quality_types
" * | smooth | disturbed | highly_disturbed ">
<!ENTITY % stroke_quality_causes_types
" * | ink_aging | pen_defect | paper_absobency |
pad_hardness | pad_surface | writer_state | pen_grip ">
<!ENTITY % inter-word_connectivity_types
" * | high | normal | low ">
<!ENTITY % intra-word_connectivity_types
" * | high | normal | low ">
<!ENTITY % relative_writing_speed_types
" * | faster | normal | slower ">
<!--Script specific information ============================ -->
<!ELEMENT script (style, meta?)>
<!ATTLIST script
type (%script_type_types;) #REQUIRED
language (%language_types;) #REQUIRED
>
<!ELEMENT style EMPTY>
<!ATTLIST style
major (%major_style_types;) #REQUIRED
connection (%connection_types;) #IMPLIED
caps (%cap_type_types;) #IMPLIED
consistency (%consistency_types;) #IMPLIED
stroke_quality (%stroke_quality_types;) #IMPLIED
embellishment (%embellishment_types;) #IMPLIED
stroke_quality_causes (%stroke_quality_causes_types;) #IMPLIED
inter-word_connectivity (%inter-word_connectivity_types;) #IMPLIED
intra-word_connectivity (%intra-word_connectivity_types;) #IMPLIED
relative_writing_speed (%relative_writing_speed_types;) #IMPLIED
>
<!-- ======================================================= -->
<!ELEMENT meta EMPTY>
<!ATTLIST meta
author CDATA #IMPLIED
email CDATA #IMPLIED
institution CDATA #IMPLIED
version CDATA #IMPLIED
created CDATA #IMPLIED
modified CDATA #IMPLIED
>
script XML tag reference
CDATA
CDATA
CDATA
CDATA
CDATA
CDATA
/>
Description: How this information was collected.
Parent Element(s):
<script/> -- Script root element.
</script>
Description: Script root element.
Parent Element(s):
None
/>
Description: Writing style.
Parent Element(s):
<script/> -- Script root element.
CONTENT DTD
content DTD Tree
content
|_(document?,
| |_EMPTY
|
|__text_block?,
| |_(properties?,
| | |_EMPTY
| |
| |__verbatim?)
| |_(#PCDATA)
|
|
|__misc_block?,
| |_EMPTY
|
|__meta?)
|_EMPTY
content XML example
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE content SYSTEM "content_.dtd">
<content>
<document
type="envelope"
intent="personal"/>
<text_block
type="addressee_address_block"
length="paragraph"
>
<properties tone="neutral" grammar="ok" spelling="bad"/>
<verbatim>
Alfred Joe
223 daoun the rode
The Bled
USA
</verbatim>
</text_block>
<meta
author="Isabelle Guyon"
email="isabelle@clopinet.com"
institution="Clopinet"
version="1.0"
created="2003-04-18-00-00"
modified="2003-04-24-00-00"/>
</content>
content DTD File
<!-- ===========================================================
content (Wanda CONTENT Modeling Language)
author: Isabelle Guyon, Katrin Fanke, Lambert Schomaker
institution: Clopinet, Fraunhofer IPK,
Rijksuniversiteit Groningen
version: 1.0
created: 2002-03-25-00-00
modified: 2003-05-08-00-00
============================================================ -->
<!ENTITY % document_type_types
" * | writing_product | note | letter | check |
greeting_card | envelope | postcard | bank_transfer
| post_sticker | hotel_registration |
foreigner_script | contract | last_will |
work_permit | tax_form | registration_form |
excerpt ">
<!ENTITY % intent_types
" * | message | bomb_threat | threat | extortion |
blackmail | pornography | child_porn |
drugs_related | financial_fraud | terrorism |
racism | personal | public ">
<!ENTITY % text_block_type_types
" * | whole_form | addressee_address_block |
sender_address_block | personal_name |
geographical_name | zipcode | legal_amount |
currency_amount | telephone_number | digits |
abbreviation | signature | paraph | plain_text ">
<!ENTITY % misc_block_type_types
" * | postal_stamp | ink_stamp | barcode |
printed_text | fingerprint | stain | drawing |
scribble | graffiti ">
<!ENTITY % text_length_types
" * | character | word | few_words | line |
paragraph | page | pages ">
<!ENTITY % tone_types
" * | kind | neutral | threatening | angry |
sad | happy ">
<!ENTITY % grammar_types " * | bad | ok | good ">
<!ENTITY % spelling_types " * | bad | ok | good ">
<!ELEMENT content (document?, text_block?, misc_block?, meta?)>
<!ELEMENT meta EMPTY>
<!ATTLIST meta
author CDATA #REQUIRED
email CDATA #REQUIRED
institution CDATA #REQUIRED
version CDATA #REQUIRED
created CDATA #REQUIRED
modified CDATA #REQUIRED
>
<!ELEMENT document EMPTY>
<!ATTLIST document
type (%document_type_types;) #REQUIRED
intent (%intent_types;) #REQUIRED
>
<!ELEMENT text_block (properties?, verbatim?)>
<!ATTLIST text_block
type (%text_block_type_types;) #REQUIRED
length (%text_length_types;) #REQUIRED
>
<!ELEMENT misc_block EMPTY>
<!ATTLIST misc_block
type (%misc_block_type_types;) #REQUIRED
>
<!ELEMENT properties EMPTY>
<!ATTLIST properties
tone (%tone_types;) #REQUIRED
grammar (%grammar_types;) #REQUIRED
spelling (%spelling_types;) #REQUIRED
>
<!ELEMENT verbatim (#PCDATA)>
content XML tag reference
</content>
Description: Root element.
Parent Element(s):
None
/>
Description: Information on the whole document.
Parent Element(s):
<content/> -- Root element.
CDATA
CDATA
CDATA
CDATA
CDATA
CDATA
/>
Description: Information on who created these data annotations.
Parent Element(s):
<content/> -- Root element.
/>
Description: Miscellaneous non-text block.
Parent Element(s):
<content/> -- Root element.
/>
Description: Text block content properties.
Parent Element(s):
<text_block/> -- Block of text.
</text_block>
Description: Block of text.
Parent Element(s):
<content/> -- Root element.
</verbatim>
Description: Verbatim transcription. Use the ISO 10646 standard to encode special characters. You can refer to characters from in the encoded repertoire by using dddd; (decimal character code) or HHHH; (hexadecimal character code, in uppercase).
Parent Element(s):
<text_block/> -- Block of text.
SCAN DTD
scan DTD Tree
scan
|_(scanner?,
| |_EMPTY
|
|__image+,
| |_(lcms)
| |_EMPTY
|
|
|__meta?)
|_EMPTY
scan XML example
<?xml version="1.0"?>
<!DOCTYPE scan SYSTEM "scan_.dtd">
<scan name="A4 Farbe quer">
<scanner driver="HP ScanJet"
feeder="flatbed"
pages="frontside"
format="A4"
orientation="landscape"/>
<image name="Archivbild"
filename="FSA%05u.jpg"
camera="frontside"
colors="rgb24"
compress="jpeg"
quality="30"
xresolution="100"
yresolution="100">
<lcms incolor="ct_lcms_rgb"
inprofile="file://c$/sg_pDir/ibis/sRGB/ibs_9403_300.icc"/>
</image>
<image name="Detailbild"
filename="FSD%05u.tif"
camera="frontside"
colors="rgb24"
compress="none"
xresolution="200" yresolution="200">
<lcms incolor="ct_lcms_rgb"
inprofile="file://c$/sg_pDir/ibis/sRGB/ibs_9403_300.icc"/>
</image>
<meta
author="Stefan Giesler"
email="st.giesler@t-online.de"
institution="Giesler Software Entwicklung"
version="1.0"
created="2003-03-10-00-00"
modified="2003-04-11-09-00"/>
</scan>
scan DTD File
<!-- ===========================================================
scan(profile) (Wanda SCAN Modeling Language)
author: Stefan Giesler <st.giesler@t-online.de>
edited by: Isabelle Guyon <isabelle@clopinet.com>
Grouped attlist args in one attlist.
Changed some default values.
Changed <info> to <meta> and put it under root element.
Added email in <meta>.
institution: Giesler Software Entwicklung
version: 1.0
created: 2003-03-10-00-00
modified: 2003-04-11-09-00
=========================================================== -->
<!ENTITY % orient "portait | landscape" >
<!ENTITY % side "frontside | backside | bothsides" >
<!ENTITY % feed "flatbed | feeder | other" >
<!ENTITY % size "A6 | A5 | A4 | A3" >
<!ENTITY % camera "frontside | backside" >
<!ENTITY % colors "bitonal | gray | rgb24 | rgb36" >
<!ENTITY % rotate "none | left | centre | right" >
<!ENTITY % compress "none | faxg3 | faxg4 | jpeg" >
<!ENTITY % xsection "none | left | right | user" >
<!ENTITY % ysection "none | top | bottom | user" >
<!-- ======================================================= -->
<!ELEMENT scan (scanner?, image+, meta?) > <!-- root tag -->
<!-- name of the scan profile -->
<!ATTLIST scan name CDATA #REQUIRED >
<!-- ======================================================= -->
<!ELEMENT scanner EMPTY >
<!ATTLIST scanner
driver CDATA "driverName"
feeder (%feed;) "flatbed"
pages (%side;) "frontside"
orientation (%orient;) "portait"
format (%size;) "A4" >
<!-- ======================================================= -->
<!ELEMENT image (lcms) >
<!ATTLIST image
name CDATA #REQUIRED
filename CDATA #REQUIRED
camera (%camera;) "frontside"
colors (%colors;) "rgb24"
rotate (%rotate;) "none"
compress (%compress;) "none"
quality CDATA "100"
xresolution CDATA "100"
yresolution CDATA "100"
xpixels CDATA "0"
ypixels CDATA "0"
xsection (%xsection;) "none"
xsecsize CDATA "0"
xseccoord CDATA "0"
ysection (%ysection;) "none"
ysecsize CDATA "0"
yseccoord CDATA "0">
<!-- ======================================================= -->
<!-- little color management system -->
<!ELEMENT lcms EMPTY>
<!ATTLIST lcms
inProfile CDATA #REQUIRED
inColor CDATA #REQUIRED
outProfile CDATA #REQUIRED
outColor CDATA #REQUIRED>
<!-- ======================================================= -->
<!ELEMENT meta EMPTY>
<!ATTLIST meta
author CDATA "anonymous"
email CDATA "anonymous@somewhere.abc"
institution CDATA "anywhere"
version CDATA "00.00"
created CDATA "YYYY-MM-DD-hh-mm-ss"
modified CDATA "YYYY-MM-DD-hh-mm-ss">
scan XML tag reference
CDATA
CDATA
CDATA
CDATA
CDATA
CDATA
CDATA
CDATA
CDATA
CDATA
CDATA
</image>
Description: Image definition block.
Parent Element(s):
<scan/> -- Root element.
CDATA
CDATA
CDATA
CDATA
/>
Description: Little color management system.
Parent Element(s):
<image/> -- Image definition block.
CDATA
CDATA
CDATA
CDATA
CDATA
CDATA
/>
Description: Information about who generated this document.
Parent Element(s):
<scan/> -- Root element.
CDATA
>
</scan>
Description: Root element.
Parent Element(s):
None
CDATA
/>
Description: Scanner information.
Parent Element(s):
<scan/> -- Root element.
PROPER DTD
proper DTD Tree
proper
|_(roi*,
| |_(vertex*)
| |_EMPTY
|
|
|__properParam+,
| |_(background,
| | |_(none?,
| | | |_ANY
| | |
| | |__homogenous?,
| | | |_ANY
| | |
| | |__textured?,
| | | |_(low?,
| | | | |_EMPTY
| | | |
| | | |__high?,
| | | | |_EMPTY
| | | |
| | | |__peaks?,
| | | | |_EMPTY
| | | |
| | | |__amount?)
| | | |_EMPTY
| | |
| | |
| | |__userdefined?,
| | | |_ANY
| | |
| | |__formdropout?,
| | | |_(image,
| | | | |_ANY
| | | |
| | | |__method,
| | | | |_ANY
| | | |
| | | |__offset)
| | | |_ANY
| | |
| | |
| | |__colordropout?,
| | | |_ANY
| | |
| | |__colorconvert?)
| | |_(channelcomp?)
| | |_(image, ...
| | |__method, ...
| | |__offset) ...
| |
| |
| |
| |__foreground?,
| | |_(reconst?,
| | | |_ANY
| | |
| | |__noise?,
| | | |_EMPTY
| | |
| | |__line?,
| | | |_(direction?,
| | | | |_(rows?,
| | | | | |_ANY
| | | | |
| | | | |__columns?,
| | | | | |_ANY
| | | | |
| | | | |__angle?)
| | | | |_EMPTY
| | | |
| | | |
| | | |__((average? |
| | | | |_ANY
| | | |
| | | |____trace? |
| | | | |_EMPTY
| | | |
| | | |____morpho? |
| | | | |_EMPTY
| | | |
| | | |____gabor?)?))
| | | |_ANY
| | |
| | |
| | |__stamp?,
| | | |_((segment |
| | | | |_ANY
| | | |
| | | |___contrast),
| | | | |_ANY
| | | |
| | | |__noise) ...
| | |
| | |__framein?,
| | | |_(share? |
| | | | |_EMPTY
| | | |
| | | |__rect?)
| | | |_(extension |
| | | | |_EMPTY
| | | |
| | | |__frame)
| | | |_EMPTY
| | |
| | |
| | |
| | |__border?)
| | |_(rect?) ...
| |
| |
| |__inout?,
| | |_(pre? |
| | | |_(scale?)
| | | |_(resolution?,
| | | | |_EMPTY
| | | |
| | | |__(bilinear? |
| | | | |_ANY
| | | |
| | | |___repeat?))
| | | |_ANY
| | |
| | |
| | |
| | |__post?)
| | |_(scale? | ...
| | |__colorout?)
| | |_(color? |
| | | |_EMPTY
| | |
| | |__pseudo?)
| | |_ANY
| |
| |
| |
| |
| |__desc?)
| |_ANY
|
|
|__meta?)
|_EMPTY
proper XML example
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE content SYSTEM "proper_.dtd">
<roi id="0">
<vertex x="20" y="50"/>
<vertex x="50" y="50"/>
<vertex x="20" y="100"/>
</roi>
<roi id="1">
<vertex x="306" y="97"/>
<vertex x="377" y="44"/>
<vertex x="454" y="100"/>
<vertex x="477" y="61"/>
<vertex x="474" y="147"/>
<vertex x="454" y="108"/>
<vertex x="376" y="143"/>
</roi>
<properParam id="0">
<background>
<homogenous/>
</background>
<foreground>
<line>
<direction>
<rows/>
</direction>
<morpho ze_horizontal="0.5" ze_vertical="20"/>
</line>
</foreground>
</properParam>
<properParam id="1">
<background>
<homogenous/>
</background>
<foreground>
<line>
<direction>
<rows/>
</direction>
<morpho ze_horizontal="22" ze_vertical="200"/>
</line>
</foreground>
</properParam>
<meta author="Martin Peng" institution="fraunhofer IPK"
version="2.0" created="2003-03-17" modified=""/>
</proper>
proper DTD File
<?xml version="1.0" encoding="UTF-8"?>
<!-- ===========================================================
proper (SIC PROPER Modeling Language)
author: Martin Peng, Katrin Franke
institution: Fraunhofer IPK
version: 2.0
created: 2002-11-18-00-00
modified: 2003-02-23-00-00
=========================================================== -->
<!-- edited with XMLSPY v5 rel. 3 U
(http://www.xmlspy.com) by Isabelle Guyon (Clopinet) -->
<!ELEMENT proper (roi*, properParam+, meta?)>
<!ELEMENT roi (vertex*)>
<!ATTLIST roi
id CDATA #IMPLIED
>
<!ELEMENT properParam (background, foreground?, inout?, desc?)>
<!ATTLIST properParam
id CDATA #IMPLIED
>
<!ELEMENT meta EMPTY>
<!ATTLIST meta
author CDATA #IMPLIED
institution CDATA #IMPLIED
version CDATA #IMPLIED
created CDATA #IMPLIED
modified CDATA #IMPLIED
>
<!ELEMENT vertex EMPTY>
<!ATTLIST vertex
x CDATA #REQUIRED
y CDATA #REQUIRED
>
<!ELEMENT background
(none?, homogenous?, textured?, userdefined?,
formdropout?, colordropout?, colorconvert?)>
<!ELEMENT foreground
(reconst?, noise?, line?, stamp?, framein?, border?)>
<!ELEMENT inout (pre? | post?)>
<!ELEMENT desc ANY>
<!ELEMENT none ANY>
<!ELEMENT homogenous ANY>
<!ELEMENT textured (low?, high?, peaks?, amount?)>
<!ELEMENT userdefined ANY>
<!ELEMENT formdropout (image, method, offset)>
<!ELEMENT colordropout ANY>
<!ELEMENT colorconvert (channelcomp?)>
<!ELEMENT reconst ANY>
<!ELEMENT noise EMPTY>
<!ATTLIST noise
size CDATA #IMPLIED
>
<!ELEMENT line
(direction?, ((average? | trace? | morpho? | gabor?)?))>
<!ELEMENT stamp ((segment | contrast), noise)>
<!ELEMENT framein (share? | rect?)>
<!ELEMENT border (rect?)>
<!ELEMENT pre (scale?)>
<!ELEMENT post (scale? | colorout?)>
<!ELEMENT low EMPTY>
<!ATTLIST low
value CDATA #IMPLIED
>
<!ELEMENT high EMPTY>
<!ATTLIST high
value CDATA #IMPLIED
>
<!ELEMENT peaks EMPTY>
<!ATTLIST peaks
value CDATA #IMPLIED
>
<!ELEMENT amount EMPTY>
<!ATTLIST amount
value CDATA #IMPLIED
>
<!ELEMENT image ANY>
<!ELEMENT method ANY>
<!ELEMENT offset ANY>
<!ELEMENT channelcomp (image, method, offset)>
<!ELEMENT direction (rows?, columns?, angle?)>
<!ELEMENT average ANY>
<!ELEMENT trace EMPTY>
<!ATTLIST trace
grayvariance CDATA #IMPLIED
derivation CDATA #IMPLIED
limit CDATA #IMPLIED
threshold CDATA #IMPLIED
>
<!ELEMENT morpho EMPTY>
<!ATTLIST morpho
se_horizontal CDATA #IMPLIED
se_vertical CDATA #IMPLIED
ze_horizontal CDATA #IMPLIED
ze_vertical CDATA #IMPLIED
>
<!ELEMENT gabor ANY>
<!ELEMENT segment ANY>
<!ELEMENT contrast ANY>
<!ELEMENT share EMPTY>
<!ATTLIST share
amount CDATA #IMPLIED
>
<!ELEMENT rect (extension | frame)>
<!ELEMENT scale (resolution?, (bilinear? | repeat?))>
<!ELEMENT colorout (color? | pseudo?)>
<!ELEMENT rows ANY>
<!ELEMENT columns ANY>
<!ELEMENT angle EMPTY>
<!ATTLIST angle
degree CDATA #REQUIRED
>
<!ELEMENT extension EMPTY>
<!ATTLIST extension
offset_x CDATA #IMPLIED
offset_y CDATA #IMPLIED
extension_x CDATA #IMPLIED
extension_y CDATA #IMPLIED
>
<!ELEMENT frame EMPTY>
<!ATTLIST frame
left CDATA #IMPLIED
top CDATA #IMPLIED
bottom CDATA #IMPLIED
right CDATA #IMPLIED
>
<!ELEMENT resolution EMPTY>
<!ATTLIST resolution
dpi (75 | 150 | 300 | 600 | 1200) #IMPLIED
>
<!ELEMENT bilinear ANY>
<!ELEMENT repeat ANY>
<!ELEMENT color EMPTY>
<!ATTLIST color
model (rgb | cmyk | gray | bw) #IMPLIED
>
<!ELEMENT pseudo ANY>
proper XML tag reference
CDATA
/>
Description: Amount of texture.
Parent Element(s):
<textured/> -- Textured background removal.
CDATA
/>
Description: Maximum slant angle in degrees.
Parent Element(s):
<direction/> -- Direction of lines.
/>
Description: Average line cleaning method. Use this procedure for the cleaning of lined and squared paper.
Parent Element(s):
<line/> -- Line removal (e.g. handwriting guide lines).
</background>
Description: Background removal.
Parent Element(s):
<properParam/> -- Parameters of the proper preprocessing.
/>
Description: What is that?
Parent Element(s):
<scale/> -- Image scaling.
</border>
Description: Border removal.
Parent Element(s):
<foreground/> -- Container of foreground filtering parameters.
</channelcomp>
Description: Channel comparison (under construction).
Parent Element(s):
<colorconvert/> -- Color conversion (under construction).
/>
Description: Color model.
Parent Element(s):
<colorout/> -- Output image color coding.
</colorconvert>
Description: Color conversion (under construction).
Parent Element(s):
<background/> -- Container of background filtering parameters.
/>
Description: Colors to be ignored (under construction).
Parent Element(s):
<background/> -- Container of background filtering parameters.
</colorout>
Description: Output image color coding.
Parent Element(s):
<post/> -- Image formating after preprocessing.
/>
Description: Lines are vertical.
Parent Element(s):
<direction/> -- Direction of lines.
/>
Description: Stamp contrast.
Parent Element(s):
<stamp/> -- Removal of stamps.
/>
Description: Textual description?
Parent Element(s):
<properParam/> -- Parameters of the proper preprocessing.
</direction>
Description: By choosing <rows/> and <columns/> the direction of the lines can be set. Lines with slant larger than specified by <angle/> compared to the horizontal or vertical are not cleaned.
Parent Element(s):
<line/> -- Line removal (e.g. handwriting guide lines).
CDATA
CDATA
CDATA
CDATA
/>
Description: Frame extension.
Parent Element(s):
<rect/> -- Inner rectangle of a frame.
</foreground>
Description: Container of foreground filtering parameters.
Parent Element(s):
<properParam/> -- Parameters of the proper preprocessing.
</formdropout>
Description: Background form removal (under construction).
Parent Element(s):
<background/> -- Container of background filtering parameters.
CDATA
CDATA
CDATA
CDATA
/>
Description: Frame rectangle vertices.
Parent Element(s):
<rect/> -- Inner rectangle of a frame.
</framein>
Description: Radical cleaning of the outer frame with a following reconstruction on the basis of the inner segments. Hereby the parameter Max indicates the size (percent) of the frame width. Furthermore, the coordinates of the inner rectangle might be explicit specified. FrameOut is under construction.
Parent Element(s):
<foreground/> -- Container of foreground filtering parameters.
/>
Description: Gabor filter.
Parent Element(s):
<line/> -- Line removal (e.g. handwriting guide lines).
CDATA
/>
Description: Value of high level texture?
Parent Element(s):
<textured/> -- Textured background removal.