{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-learning-the-indus-script","title":"Deep Learning the Indus Script","arxiv_id":"1702.00523","date":"2017-02-02","proceeding":null,"authors":["Satish Palaniappan","Ronojoy Adhikari"],"abstract":"Standardized corpora of undeciphered scripts, a necessary starting point for\ncomputational epigraphy, requires laborious human effort for their preparation\nfrom raw archaeological records. Automating this process through machine\nlearning algorithms can be of significant aid to epigraphical research. Here,\nwe take the first steps in this direction and present a deep learning pipeline\nthat takes as input images of the undeciphered Indus script, as found in\narchaeological artifacts, and returns as output a string of graphemes, suitable\nfor inclusion in a standard corpus. The image is first decomposed into regions\nusing Selective Search and these regions are classified as containing textual\nand/or graphical information using a convolutional neural network. Regions\nclassified as potentially containing text are hierarchically merged and trimmed\nto remove non-textual information. The remaining textual part of the image is\nsegmented using standard image processing techniques to isolate individual\ngraphemes. This set is finally passed to a second convolutional neural network\nto classify the graphemes, based on a standard corpus. The classifier can\nidentify the presence or absence of the most frequent Indus grapheme, the \"jar\"\nsign, with an accuracy of 92%. Our results demonstrate the great potential of\ndeep learning approaches in computational epigraphy and, more generally, in the\ndigital humanities.","url_abs":"http://arxiv.org/abs/1702.00523v1","url_pdf":"http://arxiv.org/pdf/1702.00523v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-learning-the-indus-script","repo_url":"https://github.com/tpsatish95/indus-script-ocr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[{"method_slug":"selective-search","method_name":"Selective Search"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}