Qumran Letter Restoration by Rotation and Reflection Modified PixelCNN

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

The task of restoring fragmentary letters is fundamental to the reading of ancient manuscripts. We present a method to complete broken letters in the Dead Sea Scrolls, which is based on PixelCNN++. Since the generation of the broken letters is conditioned on the extant scroll, we modify the original method to allow reconstructions in multiple directions. Results on both simulated data and real scrolls demonstrate the advantage of our method over the baseline. The implementation may be found at https://github.com/ghostcow/pixel-cnn-qumran.

Original languageEnglish
Title of host publicationProceedings - 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017
PublisherIEEE Computer Society
Pages23-29
Number of pages7
ISBN (Electronic)9781538635865
DOIs
StatePublished - 2 Jul 2017
Event14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017 - Kyoto, Japan
Duration: 9 Nov 201715 Nov 2017

Publication series

NameProceedings of the International Conference on Document Analysis and Recognition, ICDAR
Volume1
ISSN (Print)1520-5363

Conference

Conference14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017
Country/TerritoryJapan
CityKyoto
Period9/11/1715/11/17

Funding

FundersFunder number
Deutsch-Israelische Projektkooperation1330/14
Blavatnik Family Foundation
German-Israeli Foundation for Scientific Research and Development
Israel Science Foundation-145-101.3-2013

    Keywords

    • Dead-sea
    • Deep-learning
    • Pixelcnn
    • Qumran
    • Scrolls

    Fingerprint

    Dive into the research topics of 'Qumran Letter Restoration by Rotation and Reflection Modified PixelCNN'. Together they form a unique fingerprint.

    Cite this