1 / 9

Enhancement of multispectral images of ancient manuscripts

Enhancement of multispectral images of ancient manuscripts. Fabian Hollaus , Robert Sablatnig Vienna University of Technology Computer Vision Lab { holl , sab }@ caa.tuwien.ac.at. TitlE Slide With picture right. Authors Name 1, Name 2, Name 3 until this end

Télécharger la présentation

Enhancement of multispectral images of ancient manuscripts

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Enhancementofmultispectralimagesofancientmanuscripts Fabian Hollaus, Robert Sablatnig Vienna University of Technology Computer Vision Lab {holl, sab}@caa.tuwien.ac.at

  2. TitlE Slide Withpictureright Authors Name 1, Name 2, Name 3 untilthis end Affiliations {E-Mail}

  3. TitlE – slideWithout Picture Authors Name 1, Name 2, Name 3 Affiliations {E-Mail}

  4. Titel & SubtiTleWithoutpicture Authors Name 1, Name 2, Name 3 untilthis end Affiliations {E-Mail}

  5. Heading 1 Heading 1 Heading 1 • Heading 2 / Text untilthisend • Heading 3 / Text • Heading 4 / Text • Heading 5 / Text • Heading 2 / Text untilthisend • Heading 3 / Text • Heading 4 / Text • Heading 5 / Text • Heading 2 / Text untilthisend • Heading 3 / Text • Heading 4 / Text • Heading 5 / Text Titel

  6. Motivation Labeling Enhancementresult • Ancientmanuscripts • Faded out ink • Background clutter • Palimpsests (twicewrittenmanuscript) • MultiSpectral Imaging • Usedforlegibilityincreasement • Dimension reductioncanbeusedforfurtherenhancement • Applied Linear Discriminant Analysis (LDA) • Requireslabelingoftrainingdata • LDA is a superviseddimensionreductiontechnique • Requireslabeling • Automatedlabelingbased on documentanalysistechniques: • Binarization • Text linedetection Titel

  7. Motivation Picture 1 • Ancientmanuscripts • Faded out ink • Background clutter • Palimpsests (twicewrittenmanuscript) • MultiSpectral Imaging • Non-Invasive technique • Usedforlegibilityincreasement • Dimension reductioncanbeusedforfurtherenhancement • Applied Linear Discriminant Analysis • Requireslabelingoftrainingdata • Based on documentanalysistechniques • Binarization • Text linedetection Labeling Heading 1 • Heading 2 / Text untilthis end • Heading 3 / Text • Heading 4 / Text • Heading 5 / Text Titel

  8. Heading 1 Heading 1 Picture 1 AND / OR Video 1 • Heading 2 / Text untilthis end • Heading 3 / Text • Heading 4 / Text • Heading 5 / Text • Heading 2 / Text untilthis end • Heading 3 / Text • Heading 4 / Text • Heading 5 / Text Titel

  9. Titel

More Related