Deep Learning in Archiving Indus Script and Motif Information
This work presents a novel computational system for the automated digitization of image-based data from seals of the ancient Indus Valley Civilization (IVC). The objective of this system’s design is to automatically extract and archive key information from seals or images, including the script and m...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ubiquity Press
2025-05-01
|
| Series: | Journal of Computer Applications in Archaeology |
| Subjects: | |
| Online Access: | https://account.journal.caa-international.org/index.php/up-j-jcaa/article/view/175 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850158746016153600 |
|---|---|
| author | Vaishnavi Dixit Nushrat Hussain Shubham Basak Deva Atturu Debasis Mitra Ujjwal Bhattacharya |
| author_facet | Vaishnavi Dixit Nushrat Hussain Shubham Basak Deva Atturu Debasis Mitra Ujjwal Bhattacharya |
| author_sort | Vaishnavi Dixit |
| collection | DOAJ |
| description | This work presents a novel computational system for the automated digitization of image-based data from seals of the ancient Indus Valley Civilization (IVC). The objective of this system’s design is to automatically extract and archive key information from seals or images, including the script and motifs. The system operates as a pipeline comprising three deep learning models integrated with a custom-designed database. Two models form the Ancient Script Recognition network (ASR-net), which digitizes sequences of graphemes from Indus seals, similar to Optical Character Recognition for modern languages. The third model, the Motif Identification network (MI-net), identifies recurring motifs—distinctive symbols or iconographic elements with specific functional significance in the IVC. The database stores the extracted information, linking it to the respective seal images in a structured format. This end-to-end pipeline has been fully implemented, from image input to database archival. The overarching aim of this work is to support the application of automated statistical methods in the ongoing efforts to decipher the Indus script. |
| format | Article |
| id | doaj-art-e52390c2c44d4a7696c739ee6c9e35c8 |
| institution | OA Journals |
| issn | 2514-8362 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Ubiquity Press |
| record_format | Article |
| series | Journal of Computer Applications in Archaeology |
| spelling | doaj-art-e52390c2c44d4a7696c739ee6c9e35c82025-08-20T02:23:47ZengUbiquity PressJournal of Computer Applications in Archaeology2514-83622025-05-0181156–169156–16910.5334/jcaa.175173Deep Learning in Archiving Indus Script and Motif InformationVaishnavi Dixit0https://orcid.org/0009-0005-7487-0927Nushrat Hussain1https://orcid.org/0000-0002-5138-5495Shubham Basak2https://orcid.org/0000-0003-4243-7983Deva Atturu3Debasis Mitra4https://orcid.org/0000-0002-4351-1252Ujjwal Bhattacharya5https://orcid.org/0000-0002-8546-6453Florida Institute of Technology, Melbourne, FloridaIndian Statistical Institute, KolkataIndian Statistical Institute, KolkataFlorida Institute of Technology, Melbourne, FloridaFlorida Institute of Technology, Melbourne, FloridaIndian Statistical Institute, KolkataThis work presents a novel computational system for the automated digitization of image-based data from seals of the ancient Indus Valley Civilization (IVC). The objective of this system’s design is to automatically extract and archive key information from seals or images, including the script and motifs. The system operates as a pipeline comprising three deep learning models integrated with a custom-designed database. Two models form the Ancient Script Recognition network (ASR-net), which digitizes sequences of graphemes from Indus seals, similar to Optical Character Recognition for modern languages. The third model, the Motif Identification network (MI-net), identifies recurring motifs—distinctive symbols or iconographic elements with specific functional significance in the IVC. The database stores the extracted information, linking it to the respective seal images in a structured format. This end-to-end pipeline has been fully implemented, from image input to database archival. The overarching aim of this work is to support the application of automated statistical methods in the ongoing efforts to decipher the Indus script.https://account.journal.caa-international.org/index.php/up-j-jcaa/article/view/175indus valley scriptmachine learningdeep learningautomated script recognitionautomated motif identificationinformation archival |
| spellingShingle | Vaishnavi Dixit Nushrat Hussain Shubham Basak Deva Atturu Debasis Mitra Ujjwal Bhattacharya Deep Learning in Archiving Indus Script and Motif Information Journal of Computer Applications in Archaeology indus valley script machine learning deep learning automated script recognition automated motif identification information archival |
| title | Deep Learning in Archiving Indus Script and Motif Information |
| title_full | Deep Learning in Archiving Indus Script and Motif Information |
| title_fullStr | Deep Learning in Archiving Indus Script and Motif Information |
| title_full_unstemmed | Deep Learning in Archiving Indus Script and Motif Information |
| title_short | Deep Learning in Archiving Indus Script and Motif Information |
| title_sort | deep learning in archiving indus script and motif information |
| topic | indus valley script machine learning deep learning automated script recognition automated motif identification information archival |
| url | https://account.journal.caa-international.org/index.php/up-j-jcaa/article/view/175 |
| work_keys_str_mv | AT vaishnavidixit deeplearninginarchivingindusscriptandmotifinformation AT nushrathussain deeplearninginarchivingindusscriptandmotifinformation AT shubhambasak deeplearninginarchivingindusscriptandmotifinformation AT devaatturu deeplearninginarchivingindusscriptandmotifinformation AT debasismitra deeplearninginarchivingindusscriptandmotifinformation AT ujjwalbhattacharya deeplearninginarchivingindusscriptandmotifinformation |