• No results found

University of Groningen Beyond OCR: Handwritten manuscript attribute understanding He, Sheng

N/A
N/A
Protected

Academic year: 2021

Share "University of Groningen Beyond OCR: Handwritten manuscript attribute understanding He, Sheng"

Copied!
3
0
0

Bezig met laden.... (Bekijk nu de volledige tekst)

Hele tekst

(1)

University of Groningen

Beyond OCR: Handwritten manuscript attribute understanding

He, Sheng

IMPORTANT NOTE: You are advised to consult the publisher's version (publisher's PDF) if you wish to cite from

it. Please check the document version below.

Document Version

Publisher's PDF, also known as Version of record

Publication date:

2017

Link to publication in University of Groningen/UMCG research database

Citation for published version (APA):

He, S. (2017). Beyond OCR: Handwritten manuscript attribute understanding. University of Groningen.

Copyright

Other than for strictly personal use, 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), unless the work is under an open content license (like Creative Commons).

Take-down policy

If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.

Downloaded from the University of Groningen/UMCG research database (Pure): http://www.rug.nl/research/portal. For technical reasons the number of authors shown on this cover page is limited to 10 maximum.

(2)

Acknowledgements

Pursuing a PhD in a different country is extremely challenging. The success of this thesis would not have been possible without the support of many people.

Firstly, my deepest gratitude goes to my supervisor and promoter, prof. Lambert Schomaker, who provided me with the opportunity to work in the University of Groningen. I have enjoyed the meetings with him all the time and his smile always makes me relax. His invaluable guidance is not only in the PhD project and research, but also in my academic career and life. I will never forget that he wrote programs for me at the beginning to teach me how to use Bash in Linux. I am also grateful for giving me a postdoc position to continue to work together with him.

I would like to express my gratitude to prof. Jan Burgers and Petros Samara, who are partners on the MPS project. Thanks for collecting the MPS data set and publishing together. I also wish to thank Shijie Zhao, Yanfang Feng and other Chinese students, who contributed to the CERUG data set. Thanks to Marco Wiering for nice talking and helping me to read and improve my papers.

I wish to thank Jean-Paul van Oosten (JP) for sharing ideas during the PhD project and helping me to translate many letters in Dutch. Thanks to Michiel Holtkamp and Gyuhee Lee for discussing the cultural differences between the eastern and western countries in the first two years. A special thanks to Harmen de Weerd and JP who help me to translate the summary into Dutch. I thank Bowornrat Sriman for sharing the office with me during the four years. I also thank the master student, Zhenwei Shi, who worked very hard and has made contributions in the AI lab.

My thanks also go to the thesis assessment committee: prof. Cheng-Lin Liu, who provided me inspirations during the discussions on conferences; prof. Michael Biehl, who gave me valuable com-ments to improve the thesis; and prof. Eric Postma, who spent his precious time on reading my thesis. I would like to thank all the members of AI department for all the fun dinners, parties and other activities. A special thanks to Burcu for organizing the regular dinners, to Herman and Trudy for inviting me to have parties in their house, to Maruf and Pornntiwa (Pry) for sharing the office and superb talks.

I am also thankful for having many fun and happy moments with my Chinese friends in the Nether-lands. A special thanks to Chenyu Shi (Aston), Jiapan Guo, Jinfeng Shao and Yiming Bu for the traveling and dinners together.

I thank my master supervisors, prof. Lei Guo and prof. Junwei Han, from the school of automation of Northwestern Polytechnical University, where I worked before coming to Groningen. They intro-duced me into the field of pattern recognition. A special thanks to prof. Junwei Han, who taught me how to do research and to read and write academic papers.

Finally, my deepest gratitude goes to my family, my parents, my sisters for their love, encourage-ment and continuous support and help. A special thanks to my wife, Yanfang Feng, for her love and immense support.

(3)

Referenties

GERELATEERDE DOCUMENTEN

6 Historical Manuscript Dating and Localization Using A Multiple-Label Clus- tering Algorithm 89 6.1

Hinge feature proposed in (Bulacu and Schomaker, 2007). Although the Hinge feature has been successfully used in writer identification, there is one obvious drawback: it is sensitive

In this chapter we have introduced two novel curvature-free features: the run-lengths of Local Binary Pattern (LBPruns) which is the run-lengths histogram of local binary patterns

The proposed Junclets representation which is computed from a learned codebook achieves much better performance for writer identifi- cation, especially between English and

The proposed kCF and kSF can be considered as grapheme-based representations and have several attractive properties: (1) kCF and kSF cover short contour and stroke fragments of

The unsupervised cluster methods (such as regular SOM or k-means) discard the subtle difference among labels and are less discriminative in contrast to the proposed MLSOM method.

Some people I’d like to thank in random order: Frank (for your programming wisdom, the great collaboration on Flexc++ and generally being a good friend), Robert and Marieke (all

Trained hidden Markov models closer to the global optimum do not neces- sarily have a better maximum likelihood estimate (Chapter 2).. Without guidance, it is hard for hidden