• Aucun résultat trouvé

Keynote

N/A
N/A
Info
Télécharger
Protected

Academic year: 2022

Partager "Keynote"

Copied!
2
0
0

Chargement.... (Voir le texte intégral maintenant)

Texte intégral

(1)

Keynote

7

(2)

Keynote

Keynote: Writer Identification on Historical Manuscripts

Robert Sablatnig, TU Wien, AT Abstract

In recent years, Automatic Writer Identification (AWI) has received a lot of attention in the document analysis community. However, most research has been conducted on contemporary benchmark sets. These datasets typically do not contain any noise or artefacts caused by the conversion methodology. This article analyses how current state-of-the-art methods in writer identification perform on historical documents. In contrast to contemporary documents, historical data often contain artefacts such as holes, rips, or water stains which make reliable identification error-prone.

Biographie

Robert Sablatnig was born in Klagenfurt, Carinthia, Austria, in 1965. From 1992 to 2003 he was an assistant professor (Univ.Ass.), and from 2003 to 2010 an associate professor (ao Univ.Prof.) of computer vision at the Pattern Recog- nition and Image Processing Group. From 2005 to 2017 he was the head of the Institute of Computer Aided Automation. Since 2010 he is heading the Computer Vision Lab, which is part of the newly founded Institute of Visual Computing &

Human-Centered Technology (TU Wien), engaged in research, project leading, and teaching. His research interests are 3D Computer Vision including Range Finder, Stereovision, Shape from X, Registration, Calibration, Robot Vision; Automatic Visual Inspection, Hierarchical Pattern Recognition, Video data analysis (Motion and Tracking), Automated Document Analysis, Multispectral Imaging, Virtual- and Augmented Reality, and Applications in Industry and Cultural Heritage Preserva- tion.

8

Références

Télécharger maintenant ( PDF - 2 Page - 186.86 KB )

Documents relatifs

Probabilistic Models of Visual Appearance For Object Identity, Class, and Pose Inference

Schmid, Accurate Object Detection with Deformable Shape Models Learnt from Images, in: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), ISSN

Spatial tracking of small ruminants on pasture

We propose to use different types of computer vision techniques based on color space manipulation, thresholding, feature extraction, texture classification and shape analysis in order

PRAXIS: Towards automatic cognitive assessment using gesture recognition

Ng, Learning hierarchical invariant spatio- temporal features for action recognition with independent subspace analysis, in: Computer Vision and Pattern Recognition (CVPR), 2011

Real-time markerless tracking for augmented reality: the virtual visual servoing framework

His research interests include real-time 3D tracking, robust statistics, nonrigid motion, visual servoing, computer vision, and the application of these techniques to robotics

From Dense 2D to Sparse 3D Trajectories for Human Action Detection and Recognition

Wang, “Hierarchical recurrent neural network for skeleton based action recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp..

Image compression of Surface defects of the hot-rolled steel strip using discrete Cosine Transform and Discrete Wavelet Transform

Automatic quality control of surface of hot rolled steel using computer vision systems is a real time application, which requires highly efficient Image compression

A Bayesian Framework for Active Artificial Perception

His current research interests focus on inertial sensor data integration in computer vision systems, Bayesian models for multimodal perception of 3D structure and motion, and

Direct matching for improving image-based registration

• The registration problem has been widely studied in the field of computer vision, direct methods solve the problem by minimizing the photometric and the