Computer aided restoration of handwritten character strokes

dc.contributor.author

Sober, B

dc.contributor.author

Levin, D

dc.date.accessioned

2019-12-17T16:04:23Z

dc.date.available

2019-12-17T16:04:23Z

dc.date.issued

2017-08-01

dc.date.updated

2019-12-17T16:04:20Z

dc.description.abstract

© 2017 Elsevier Ltd This work suggests a new variational approach to the task of computer aided segmentation and restoration of incomplete characters, residing in a highly noisy document image. We model character strokes as the movement of a pen with a varying radius. Following this model, in order to fit the digital image, a cubic spline representation is being utilized to perform gradient descent steps, while maintaining interpolation at some initial (manually sampled) points. The proposed algorithm was used in the process of restoring approximately 1000 ancient Hebrew characters (dating to ca. 8th–7th century BCE), some of which are presented herein and show that the algorithm yields plausible results when applied on deteriorated documents.

dc.identifier.issn

0010-4485

dc.identifier.issn

1879-2685

dc.identifier.uri

https://hdl.handle.net/10161/19605

dc.language

en

dc.publisher

Elsevier BV

dc.relation.ispartof

CAD Computer Aided Design

dc.relation.isversionof

10.1016/j.cad.2017.04.005

dc.subject

Science & Technology

dc.subject

Technology

dc.subject

Computer Science, Software Engineering

dc.subject

Computer Science

dc.subject

Computer aided design

dc.subject

Hebrew ostraca

dc.subject

First temple period

dc.subject

Historical document analysis

dc.subject

INSCRIPTIONS

dc.subject

MOVEMENTS

dc.subject

WRITER

dc.subject

MODEL

dc.title

Computer aided restoration of handwritten character strokes

dc.type

Journal article

duke.contributor.orcid

Sober, B|0000-0001-5090-5551

pubs.begin-page

12

pubs.end-page

24

pubs.organisational-group

Trinity College of Arts & Sciences

pubs.organisational-group

Duke

pubs.organisational-group

Mathematics

pubs.publication-status

Published

pubs.volume

89

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
1602.07038v2.pdf
Size:
6.41 MB
Format:
Adobe Portable Document Format
Description:
Accepted version