UvA-DARE is a service provided by the library of the University of Amsterdam (https://dare.uva.nl)
UvA-DARE (Digital Academic Repository)
Style characterization of machine printed texts
Bagdanov, A.D.
Publication date
2004
Link to publication
Citation for published version (APA):
Bagdanov, A. D. (2004). Style characterization of machine printed texts.
General rights
It is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons).
Disclaimer/Complaints regulations
If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: https://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible.
Acknowledgements s
«Who«Who should I thank?"
-Olinn Shivers, The Scheme Shell Reference Manual. Cambridge, Septemberr 4, 1994 II can say, without fear of resorting to hyperbole, that this thesis would not have beenn possible without the help and support of many people. First and foremost, I must thankk my co-promotor Marcel Worring and my promotor Arnold Smeulders. Marcel taughtt me about integrity and perseverance, and Arnold showed me how to be bold and takee chances. They have both contributed actively (as they well know), and passively
(ass they might not know) to this work, and I thank them. Much appreciation is also due too the members of my doctoral committee for taking time out of their busy schedules to revieww this thesis, provide insightful suggestions and commentary on the manuscript, andd serve on the committee.
Manyy people actively contributed to the technical development of several chapters inn this dissertation. The guidance of Rein van den Boomgaard was instrumental in thee design and success of the nonlinear, autocorrelation-driven diffusion approach of chapterr 5. The Greedy Inchworm Algorithm of chapter 4 was rescued in the eleventh hourr by the extremely deft analysis of Leo Dorst, who immediately recognized the unnaturalnesss of the Euclidean metric for what we were using it for and noticed that thee Manhattan metric, in addition to being more natural, quite nicely circumvents the problemss caused by the roundness of the Euclidean distance.
Andd now a big shout out to all my ISIS homies, past and present. Frank Seinstra andd Joost van de Weijer, I hope you know that I would have long ago lost the tat-teredd remnants of my sanity without your friendship and support over the last four years.. Thank you. Jan-Mark, you really know what it is to go above and beyond thee call of duty as a friend and colleague, and for that I am eternally in your debt. Propss out to Aristeidis Diplaros, my current and long-time officemate, along with my formerr MIA compatriots Thang Pham, Minh Hoang, Marc Navarro, Ceés Snoek, and Jeroenn Vendrig. Your patience with my belligerent, computer-strangling, fist-shaking, uninterupted-torrent-of-obscenitiess style of programming is admirable, to say the least. Denniss Koelma, in addition to being the wizardliest programmer and software engineer thatt I have ever had the pleasure of working with, deserves thanks for his support and patiencee with my, um..., leanings toward unconventional programming languages and softwaree design. Oh, and Erik and Sénnay... I'm still waiting for a doubles re-match, if wee can actually find the ping-pong table. Thanks to Wilko Quak for being the first of
146 6
myy new colleagues to welcome me into his home, to Geert Streekstra for not letting me spendd my fist Christmas in The Netherlands alone, and to Carlo de Boer for making my hoistt the mainsail, Edo Poll was the first person to introduce me to the complexities off image processing software design, for which I thank him, and he almost convinced mee that C + + isn't the odious abomination that it so very much is, but I guess I'll takee that up with him privately. Many, many thanks also to Virginie, Saskia, and Edwinn for enduring my endless stream of questions and for sometimes accomplishing thee impossible.
Manyy members of the our sister group IAS also deserve recognition here. Hey Joris,, I got the ligatures right this time, without having to ask you again (of course, I'mm not using Times, though). Much appreciation also to Stefan, Josep, and Nikos (Massios)) for being patient while I lounged around on the couch in their office extolling thee vicissitudes of operating systems and other worthless things. Nikos (Vlassis) and Sjaakk Verbeek also deserve my thanks for always contributing freely to technical and abstractt discussions on any number of topics, Leo Dorst deserves recognition for his understanding,, enthusiasm, and all around scientific wizardliness. I wish him continued successs in his struggle against the forces of geometric orthodoxy.
Throughoutt my stay in Holland I have been supported by a diverse collection of friendss who kept me going through the darkest and brightest of hours. Chryssi and Tony befriendedd me in my first hours in Holland, and I thank them for keeping the wheels off science well lubricated and for their constant moral support. Much appreciation for Lisaa and Gustav too, for great vegetarian food on short notice, the great view, and forr always knowing whether to distract me or to tell me to get back to work. Thanks alsoo to Maaike, Pieter, and Nina for their friendship, movie nights, and for brilliantly demonstratingg (through counter-example) how typical Dutch families operate.
II don't know how I would have made it through to the end of this without the supportt of Rebecca, and I don't like to think about it. I thank her deeply for all the love,, sandwiches, and understanding.
