Tutorials

Tutorial 1: Volker Märgner, Technische Universität Braunschweig, Germany
Tutorial 2: Nicolai Petkov, University of Groningen, Netherlands

Tutorial 1


Volker Märgner
Technische Universität Braunschweig, Germany

Title: Historical Document Processing as an Application Field for Pattern Recognition Research
Abstract: Massively scanning of historical books by companies or libraries all over the world makes images of historical books available for everybody who has access to the internet. Unfortunately only the given Meta data can be used for searching but for the work on the content again the original document or a printed copy has to be used.
Automatic analysis and processing of scanned historical documents can help to overcome this disadvantage by using image processing and pattern recognition methods and tools.
In my talk I will present an overview about problems and solutions for historical document processing. Present a system for analyzing and processing of historical documents, the modules and some solutions that show how the humanities can take advantage of pattern recognition knowledge to ease their research and open doors for new applications.
Finally some results from an ongoing project for historical Arabic manuscript
Biography: Volker Märgner received his diploma (Dipl.-Ing.) and doctorate (Dr.-Ing.) degrees in electrical engineering from the Technische Universität Carolo Wilhelmina zu Braunschweig (TUBS), Germany, in 1974 and 1983 respectively. Since 1983, he has been working at the TUBS. Currently he is a member of the research and teaching staff at the Institute for Communications Technology, in the position of an academic director. He lectures in image processing and pattern recognition. His main areas of research are image processing and pattern recognition. Currently, he is working on image pre-processing and pattern recognition methods and their application to industrial quality control as well as to the recognition of cursive handwriting on documents. He developed recognizer for printed German text and for German handwritten words. Robust pre-processing and feature extraction with an HMM based recognizer are the key features of this solution. Since 1991 he is also working on Arabic text recognition, at the beginning on printed text recognition thereafter on handwritten Arabic word recognition. This work is done in close cooperation with Tunisian universities. He developed the IFN/ENIT-database of handwritten words in 2002 and organizes the biennial competition on Arabic handwriting recognition within the ICDAR conference since 2005. He worked on the important task of system evaluation, in particular on the evaluation of document segmentation results. He published more than 60 papers including journal papers and book chapters. He is a member of program committees of conferences and workshops. He is a reviewer for international journals, including IEEE-PAMI, IJDAR, and PR and he is a member of VDE/VDI, DAGM, IAPR (TC10, TC11), and IEEE.processing are shown.


Tutorial 2

Nicolai Petkov
University of Groningen, Netherlands
Lecture 1
Title: 2D Gabor functions and filters for image processing and computer vision
Abstract Neuro-physiologic background: properties of simple and complex cells in cortical areas V1/V2. Two-dimenisonal Gabor functions as models of the receptive fields of simple cells. Mathematical parametrisation of receptive field properties: preferred orientation, spatial frequency, bandwidth, shape. Semi-linear Gabor filters and banks of such filters. Complex cells and Gabor energy filters. Gabor filters vs. Canny ede detectors. Gabor filter banks and texture descriptors. CORF filters as more realistic models of simple cells.
Lecture 2
Title:
Contour detection by surround suppression of texture
Abstract The masking role texture in the perception of contours: psychophysical and neuro-physiological evidence. Computational models of surround suppression in complex cells and 2D Gabor filters. Improving the performance of contour detectors by surround suppression of texture.
Biography: Nicolai Petkov is professor of computer science at the University of Groningen since 1991. In the period 1998-2009 he was scientific director of the Institute for Mathematics and Computer Science. He works in the field of brain-inspired visual pattern recognition. See www.cs.rug.nl/~petkov.