Laboratoire Informatique, Image et Interaction (L3i)

Title : Document Image Pre-processing : Segmentation and Slant Removal
Abstract : The document image preprocessing is essential in all the Document Analysis Systems. The document segmentation can include many different tasks e.g. image-text discrimination, column segmentation, line or word extraction etc.
In my current research, I try to deal with them by a common approach, based on Wigner-Ville Distribution.
On the other hand the Slant Removal, the shifting of text to the vertical position, is also an old problem that has been solved by correcting words or text lines, separately.
However this requires segmentation that is not successfully 100%. Thus, extra noise is introduced in the result. Recently, I work a methodology that the Slant is removed by the whole page without segmentation.

Short CV : Ergina Kavallieratou was born in Kefalonia, Greece, in 1973. She received her Diploma in Electrical and Computer Engineering in 1996 from the Polytechnic School of the University of Patras and her PhD in Handwritten Optical Character Recognition and Document Image processing from the same department in 2000. She has worked as guest researcher in the Signals, Systems and Radiocomunications Laboratory of the Dept. of Telecommunications Engineering of the Polytechnic School of Madrid (1997-1998), in the Institute of Communication Acoustics of Ruhr-Universitaet Bochum, Germany (2000, 2001), Computer Science & Engineering, Lehigh University - USA (December 2009), CVC, Universidad de Barcelona (June 2011). During the years 2002-2004, she was an Assistant Professor of Audio Processing in Dept. of Audio and Musical Instruments Technology in the Technological Educational Institute of Ionian Islands, Greece. She teaches in Greek Open University, since 2001. Since September 2004, she is a member of the teaching staff of the department of Information and Communication System Engineering, University of the Aegean, as Assistant Professor since 2013. Her research interests include Optical Character Recognition, Document Image Analysis, Computer Vision and Pattern Recognition.​She is a board member of the Greek Artificial Intelligence Association.

Title : Stylometry and Text Mining Applications
Abstract : Stylometry is the line of research dealing with the quantification of writing style. Several text categorization tasks are mainly based on stylistic rather than topical differences among the documents, including authorship attribution, author profiling, text genre detection, and plagiarism detection. In this presentation, the main stylometric approaches will be presented and their pros and cons will be discussed.
Then, the application of a stylometric approach to plagiarism detection will be presented. More specifically, in intrinsic plagiarism detection (i.e., when there is no reference collection) the plagiarized passages within a document can only be found based on stylistic inconsistences. Moreover, extrinsic plagiarism detection (i.e., when the plagiarized passages come from a given reference document collection) can be significantly enhanced using stylistic information.

Short CV : Dr. Efstathios Stamatatos received the diploma degree in electrical engineering (1994) and the doctoral degree in electrical and computer engineering (2000), both from the University of Patras, Greece. In the past, he has worked at the Polytechnic University of Madrid (1998) as a visiting researcher, the Austrian Research Institute for Artificial Intelligence as a post-doc researcher (2001-2002) and the Technological Educational Institute of Ionian Islands (2003-2004) as an assistant professor. Since 2004 he is a member of the faculty staff of the Department of information and Communication Systems Engineering, University of the Aegean (currently an associate professor). His research interests include text mining, natural language processing, information retrieval, and machine learning. He is the director of the Artificial Intelligence Lab., University of the Aegean, and has co-organized several international evaluation campaigns on plagiarism detection, authorship attribution and social software misuse.
Home page : http://www.icsd.aegean.gr/lecturers/stamatatos/

publie le vendredi 25 septembre 2015