R
Robert Sablatnig
Researcher at Vienna University of Technology
Publications - 205
Citations - 3030
Robert Sablatnig is an academic researcher from Vienna University of Technology. The author has contributed to research in topics: Image segmentation & Multispectral image. The author has an hindex of 27, co-authored 194 publications receiving 2654 citations. Previous affiliations of Robert Sablatnig include University of Vienna & University of Engineering and Technology, Peshawar.
Papers
More filters
Proceedings ArticleDOI
MSIO: MultiSpectral Document Image BinarizatIOn
TL;DR: A methodology which detects a target ink in document images by taking into account this additional information is presented, which achieved the highest performance at the MultiSpectral Text Extraction (MS-TEx) contest 2015.
Proceedings ArticleDOI
Improving OCR Accuracy by Applying Enhancement Techniques on Multispectral Images
TL;DR: By applying the enhancement method the OCR performance is increased in the case of degraded writings, compared to OCR results gained on unprocessed multispectral images and to O CR results achieved on images, which have been produced by applying unsupervised dimension reductions.
Proceedings Article
Classification of gothic and baroque architectural elements
TL;DR: The current paper targets the problem of classification of Gothic and Baroque architectural elements called tracery, pediment and balustrade, based on clustering and learning of local features and yields a high classification rate.
Proceedings ArticleDOI
Multispectral imaging for analyzing ancient manuscripts
Martin Lettner,Robert Sablatnig +1 more
TL;DR: The study shows the effectiveness of using multispectral data for a computer aided analysis of ancient text documents and compares the results of the proposed segmentation method to traditional methods based on color images as well as gray level images.
Journal ArticleDOI
Verifying molecular clusters by 2-color localization microscopy and significance testing.
Andreas M. Arnold,Magdalena C. Schneider,Christoph Huesson,Robert Sablatnig,Mario Brameshuber,Florian Baumgart,Gerhard J. Schütz +6 more
TL;DR: A 2-Color Localization microscopy And Significance Testing Approach (2-CLASTA) is introduced, providing a parameter-free statistical framework for the qualitative analysis of two-dimensional SMLM data via significance testing methods and yields p-values for the null hypothesis of random biomolecular distributions, independent of the blinking behavior of the chosen fluorescent labels.