NDLI: Homogenization of 2D & 3D Document Formats for Cuneiform Script Analysis

Please wait, while we are loading the content...

Space Displacement Localization Neural Networks to locate origin points of handwritten text lines in historical documents

Learning Texture Features for Enhancement and Segmentation of Historical Document Images

Template generation from postmarks using cascaded unsupervised learning

A Framework for Efficient Transcription of Historical Documents Using Keyword Spotting

Selecting Autoencoder Features for Layout Analysis of Historical Documents

Publication Date Estimation for Printed Historical Documents using Convolutional Neural Networks

Handwritten Text Recognition Results on the Bentham Collection with Improved Classical N-Gram-HMM methods

Layout Analysis Algorithm Based on Probabilistic Graphical Model for Dunhuang Historical Documents

Large scale style based dating of medieval manuscripts

Cost-Effective Information Extraction from Lists in OCRed Historical Documents

Combining Learned Script Points and Combinatorial Optimization for Text Line Extraction

Homogenization of 2D & 3D Document Formats for Cuneiform Script Analysis

Historical Typewritten Document Recognition Using Minimal User Interaction

Document Image Binarization using LSTM: A Sequence Learning Approach

A Character Style Library for Syriac Manuscripts

Europeana Newspapers OCR Workflow Evaluation

Clustering Historical Documents Based on the Reconstruction Error of Autoencoders

Retrieving Cuneiform Structures in a Segmentation-free Word Spotting Framework

Homogenization of 2D & 3D Document Formats for Cuneiform Script Analysis

Content Provider	ACM Digital Library
Author	Massa, Judith Bogacz, Bartosz Mara, Hubert
Abstract	In the Digital Humanities, text sources can be digitized using various methods resulting in different data representations of related documents. This presents an increased challenge for clay tablets with cuneiform script, which is one of the oldest scripts written by hand, used in the ancient Middle East for more than three millennia. Using a 3D-Scanner to acquire a cuneiform tablet or a manually created line tracing are two completely different representations of the same type of text source. Additionally, a line tracing can be born-digital as a vector graphic or it can be a raster image of a drawing with ink on paper. Each representation is typically processed with its own tool-set and the textual analysis is therefore limited to a certain type of digital representation. In this work we present a work-flow for unification of the three most common graphical representations of cuneiform tablets. The first approach vectorizes the manually created retro-digitized tracings by skeletonization and applies pattern matching to extract the wedges, which are the radical elements of cuneiform script. Secondly, the born-digital drawings also require pattern matching as the curved lines are set differently by each draftsperson. Due to the density of wedges, a subsequent conflict resolution is applied to both types of line drawings. As cuneiform characters are written by hand in 3D, we show the segmentation and extraction of wedges from high-resolution 3D-models. The result is one representation exported as Scalable Vector Graphic (SVG), which is used for character retrieval for a future Optical Character Recognition (OCR) as ultimate goal.
Starting Page	115
Ending Page	122
Page Count	8
File Format	PDF
ISBN	9781450336024
DOI	10.1145/2809544.2809549
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2015-08-22
Publisher Place	New York
Access Restriction	Subscribed
Subject Keyword	Data homogenization 3d-scanning Digital humanities Skeletonization Segmentation Conflict resolution 3d handwritten script Feature extraction Cuneiform script Data normalization Pattern matching
Content Type	Text
Resource Type	Article

Central Library (ISO-9001:2015 Certified)
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal, India | PIN - 721302

See location in the Map
03222 282435
Mail: support@ndl.gov.in

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in