Zur Seitenansicht
 

Titelaufnahme

Titel
MultiSpectral Image Binarization using GMMs
Verfasser / Verfasserin Hollaus, Fabian ; Diem, Markus ; Sablatnig, Robert
Erschienen in
16th International Conference on Frontiers in Handwriting Recognition (ICFHR 2018), Niagara Falls, New York, 2018, S. 570-575
Erschienen2018
SpracheEnglisch
DokumenttypAufsatz in einem Sammelwerk
Schlagwörter (EN)MSI / Binarization / GMM
Projekt-/ReportnummerEuropean Union's Horizon 2020: 674943
ISBN9781538658758
URNurn:nbn:at:at-ubtuw:3-3784 Persistent Identifier (URN)
DOI10.1109/ICFHR-2018.2018.00105 
Zugriffsbeschränkung
 Das Werk ist frei verfügbar
Dateien
MultiSpectral Image Binarization using GMMs [0.84 mb]
Links
Nachweis
Klassifikation
Zusammenfassung (Englisch)

MultiSpectral Imaging enhances the study of degraded historical documents. It allows for visualizing washed out or even invisible ink but also improves the automated analysis because of a denser spectral sampling. We present a new methodology for binarization of multispectral document images that groups spectral signatures of different sources by fitting two Gaussian Mixture Models (GMMs) with Expectation Maximization. Both GMMs assign cluster labels to the multispectral samples and the clustering results are combined for the identification of the handwriting regions. The method is evaluated on the ICDAR 2015 MS-TEx dataset. Results on this publicly available benchmarking set are encouraging.

Notiz
Statistik
Das PDF-Dokument wurde 12 mal heruntergeladen.