Joint Glossary of Forensic Document Examination and Pattern Recognition Inés Baldatti Erika Griechisch Banco Central de la República Argentina University of Szeged, Hungary Buenos Aires, Argentina H-6720 Szeged, Árpád tér 2. Email: inesbaldatti@gmail.com Email: grerika@inf.u-szeged.hu Abstract—In this paper we introduce an open, scientific glos- the reference marked on the page is only Google search. sary which uses MediaWiki engine to the forensic examiner and The multilingua lexicon of European Network of Forensic pattern recognition scientific communities. Besides our aim to Science Institutes (ENFSI) is a great contribution created by find editors from these communities who contribute to extend the glossary and make it as complete as possible, we would like several forensic institute, founded in 1999. It contains several to translate the terms from English to other languages, e.g. Por- words in many languages, but it is only a dictionary, without tuguese, German, Chinese, Japanese, Arabian. The contribution explanation, descriptions. can be started with translating the existing words at the glossary. The second part of our work when the glossary become be more B. Authors completed, will consist into create the very understanding and useful glossary. The first author Inés Rosa Baldatti is a forensic document examiner, analyst of Payment Systems at the Central Bank I. I NTRODUCTION of Argentina Republic. The second author Erika Griechisch In the last few years there were more and more communi- is a PhD student at the University of Szeged (Institute of cation and joint research between the forensic examiners and Informatics), her topic is online signature verification. Further pattern recognition scientists. These two communities can ef- authors are every colleague who would like to contribute. ficiently work together, if they understand the terms from both 1) Beginning: The authors met at First International Work- sciences. We have seen and heard on meetings, conferences, shop on Automated Forensic Handwriting Analysis (AFHA) workshops, and during discussions it is a necessity to have in 2011, Beijing, China. In that opportunity it was clear the a useful, extendable glossary, and dictionary which helps the necessity to get a good understanding and a fluid contact common work. among professionals worldwide. So, we decide to make this Our aim is to create a glossary and a dictionary with work, that takes a long time and dedication, and responsibility. the important terms of the forensic science for the foren- 2) Creating: We read papers and books and websites, and sic document examiners and pattern recognition experts in extract the terms from them keeping the meaning. different languages. We are considering even the different expressions among countries who share the same language II. T ECHNICAL BACKGROUND in order to obtain a better understanding into our fields no Nowadays a glossary or dictionary which is available only matter where we are from. Thinking and hoping this work will in printed version is not really useful. An online glossary is be a useful tool for both: the forensic and pattern recognition more useful than a printed one and it can be easily printed if it communities. is necessary. Several criteria should meet, which are feasible The long name of the glossary is Glossary of Forensic only if the glossary is an online one. Document Examination and Pattern Recognition and the short name is GoFDER. The site is availabe on the http://projects. dfki.uni-kl.de/gofder/index.php URL. Figure 1 shows the logo of the glossary which depicts an important tool of the forensic scientist. A. Related work An offline glossary from 1999 is [2] which integrates first time in publishing terms from forensic science. The Forensic Science Central is a great contribution with links and forum, but its own glossary [3] contains only a small portion of def- inition, there is no dictionary and it is not extendible. Similar holds for the website of ThinkQuest [4], in addition there are less terms and the terms there were not described by experties, Fig. 1. The logo of the project Fig. 2. WikiEditor: WikiText and Preview (above), Changes (below) The most important criterion is the expandability of the glossary with dictionary, a basic MediaWiki is not sufficient. glossary. There will be always terms which can be added, not Thus we added other extension to improve the efficiency. In necessary because there incompleteness of the glossary itself the following we describe each of them. rather the expension of the scientist. Regarding the expansion, B. Semantical MediaWiki it is much easier to correct errors in an existing online website than a book. Semantical MediaWiki (often noted by SMW) is an exten- Other consideration was the possibility of localization of the sion of MediaWiki that helps to search, organise, tag, browse, glossary. We know for the translation part it is necessary to be evaluate and share the wiki’s content [8] since 2005. clean and easy otherwise we can expect only few translators. While a traditional Wikipedia site contains text which is In this section we introduce and describe the MediaWiki useful and can be processed easily by humans, it is not easy package and its extensions which were most suitable for our to understand or evaluate for a computers. The Semantical Me- purposes. diaWiki helps to extend a capability of a Wiki site by adding annotations, which makes wiki a collaborative database. A. MediaWiki Semantical MediaWiki itself has several extension too, we added the Semantic Glossary to our website, which helps to MediaWiki (MW) is a versatile package, written in PHP describe terms with the Terminology page of the wiki. The and originally developed for use on Wikipedia since 2002. It reader of a page just point to a word with the mouse and if is very widespread, well-documented, can handle any kind of the Terminology page contains that word, it’s description will media easily (links, images, videos, etc), moreover it is open- appear in a small box below the word. source which makes it easier to discover and fix any kind of bugs. The MediaWiki package quite flexible and further C. Translate extension functionalities can be easily integrated to a basic MediaWiki The Translate extension makes MediaWiki a powerful tool website. to translate every kind of text. [7] MediaWiki uses a markup language called wikitext to use It runs inside MediaWiki and has many features for transla- basic formatting so the users without knowledge of HTML tors, however its usage is very simple. After a page is marked can edit the pages easily. We added the WikiEditor extension with the tag, the extension automatically to the GoFDER website, which allows the users to see 3 splits the text between the translation tag to translation units. different view during the editing. The first one is the plain The arrangment of the translation units can be approved or wikitext, the second is a preview, the third one shows the redefined if it is necessary. According to the default settings differences between the previous version of the page and the each translation unit is one paragraph. After the arrangement current (edited) version. Thus if someone is new in wikitext of the translation units are saved, the page can be translated markup language, s/he can simply check the Preview before via a translation tool. Figure 3 and 4 show two view of a submission, see Figure 2. translation page, translators can use which are more convinient In order to achieve our goals, to create a multilingual for them. Fig. 3. Translate a page: List view Fig. 4. Translate a page: Proofread view Users can choose the language they intend to translate B. Translation from a list. On the GoFDER website there is a predefined We would like to translate the terms from English primarily list on the top of all the translatable webpages which shows to Spanish, German and Hungarian. In the same way to the languages we primarily intend to find translators (the increase the dictionary, we plan to add new languages as well. first author of this paper is responsible mainly for Spanish We hope to attain contributors who can create the Portuguese, translations, the second is about Hungarian). Nevertheless Chinese, Japanese, Arabian, etc translation. there is no language restrictions, contributors are welcome to The translations are available for a page if it is marked for translate to any language. translation. Every registered user can translate sites, but only If an original English wikipage (which is marked for trans- translation administrators can mark pages for translation and lation) has any changes, on the top of the page there will be a confirm completed translations. If a user creates a page and note about that and each unit which is effected will be marked s/he is member of the Translation group, s/he can mark it for as outdated translation. translation. if s/he is not member of this group, she can ask III. C ONTRIBUTION someone from the Translation group. More details about editing and translating are available on Recently (end of May, 2013) the glossary has 20 pages the Contribution page of the website. (terms), the dictionary has 561 English words with Spanish translation and some Hungarian translation as well. IV. C ONCLUSION Here we presented the conception and initation of our work. A. New terms The technical background of the glossary have been prepared. We encourage forensic document examiners to extend the However we are still open for suggestions and ideas to improve glossary and the dictionary as well, comment the recent terms the website. From now on the main part of the project is to add on the discussion pages, ask if something is not clear or new terms, specify and extend the existing ones, add examples complete. We want to keep our glossary professional, so on and explanation as many as possible. our wiki site it is not possible to edit or modify pages without We expect as an outcome of our common effort with the registration. After registration and login, users can modify the contributors that we can provide a useful, up-to-date and pages. beneficial glossary for the scientific community. ACKNOWLEDGEMENT The second author was supported by the TÁMOP-4.2.4B/2- 11/1-2012-0001 project. R EFERENCES [1] GoFDER website (May 2013 – ) http://projects.dfki.uni-kl.de/gofder/ [2] John C. Brenner: Forensic Science Glossary, 1999, CRC Press (184 pages), http://www.crcpress.com/product/isbn/9780849311963 [3] Forensic Science Glossary of Forensic Science Central (May 2013) http://www.forensicsciencecentral.co.uk/glossary.shtml [4] ThinkQuest Glossary (May 2013) http://library.thinkquest.org/04oct/00206/text glossary.htm [5] MULTILINGUA lexicon (May 2013) http://www.ies.krakow.pl/multilingua/welcome [6] MediaWiki website (May 2013), http://www.mediawiki.org [7] Translate Extension (May 2013) http://www.mediawiki.org/wiki/Extension:Translate [8] Semantic MediaWiki (May 2013), http://semantic-mediawiki.org Search Search Go Search History View source Discussion Page Navigation GoFDER Main page Glossary Dictionary lossary of Forensic Document Examination and Pattern Recognition Recent changes Other languages: Arabic • German • English • Spanish • Hungarian Help This is the test website of the GoFDER project (Glossary of Forensic Document Examination & Pattern Recognition). Personal tools English Our aim is to create a glossary and a dictionary with the important terms of the forensic science for the forensic document examiners and pattern recognition experts in different languages. We are considering even the different Create account expressions among countries who share the same language in order to obtain a better understanding into our Log in fields no matter where we are from. Thinking and hoping this work will be a useful tool for both: the forensic and pattern recognition community. Toolbox If you have any suggestion, related request or just want to contribute, please contact us or/and register! What links here Looking forward to your comments, Related changes Special pages Inés Baldatti and Erika Griechisch Printable version Permanent link Browse properties Fig. 5. Main page Search Search Go Search Special page Navigation All pages Main page All pages Glossary All pages Dictionary Display pages starting at: Recent changes Display pages ending at: Namespace: Help (Main) Hide redirects Go Personal tools English Characteristic Class characteristic Comparison Contribution Copybook form Dictionary Create account Document Document Examiner Examination Log in Exemplar Exemplar/en Exemplar/hu Expert Witness Forensic science GoFDER Toolbox GoFDER/de GoFDER/en GoFDER/es Special pages GoFDER/hu Graphology Graphology/en Habit Habit/en Handwriting Handwriting/en Handwriting recognition Infrared luminescence Infrared luminescence/en Infrared luminescence/es Infrared luminescence/hu List of abbreviations List of writings Main Page/de Main Page/en Main Page/es Main Page/hu Signature Signature/en Signature/es Signature/hu Privacy policy About Glossary of Forensic Document Examination & Pattern Recognition Disclaimers Cavendish Skin Fig. 6. Glossary – All pages