Deep Aramaic: Towards a synthetic data paradigm enabling machine learning in epigraphy.
Epigraphy is witnessing a growing integration of artificial intelligence, notably through its subfield of machine learning (ML), especially in tasks like extracting insights from ancient inscriptions. However, scarce labeled data for training ML algorithms severely limits current techniques, especia...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2024-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0299297&type=printable |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846129419798708224 |
|---|---|
| author | Andrei C Aioanei Regine R Hunziker-Rodewald Konstantin M Klein Dominik L Michels |
| author_facet | Andrei C Aioanei Regine R Hunziker-Rodewald Konstantin M Klein Dominik L Michels |
| author_sort | Andrei C Aioanei |
| collection | DOAJ |
| description | Epigraphy is witnessing a growing integration of artificial intelligence, notably through its subfield of machine learning (ML), especially in tasks like extracting insights from ancient inscriptions. However, scarce labeled data for training ML algorithms severely limits current techniques, especially for ancient scripts like Old Aramaic. Our research pioneers an innovative methodology for generating synthetic training data tailored to Old Aramaic letters. Our pipeline synthesizes photo-realistic Aramaic letter datasets, incorporating textural features, lighting, damage, and augmentations to mimic real-world inscription diversity. Despite minimal real examples, we engineer a dataset of 250 000 training and 25 000 validation images covering the 22 letter classes in the Aramaic alphabet. This comprehensive corpus provides a robust volume of data for training a residual neural network (ResNet) to classify highly degraded Aramaic letters. The ResNet model demonstrates 95% accuracy in classifying real images from the 8th century BCE Hadad statue inscription. Additional experiments validate performance on varying materials and styles, proving effective generalization. Our results validate the model's capabilities in handling diverse real-world scenarios, proving the viability of our synthetic data approach and avoiding the dependence on scarce training data that has constrained epigraphic analysis. Our innovative framework elevates interpretation accuracy on damaged inscriptions, thus enhancing knowledge extraction from these historical resources. |
| format | Article |
| id | doaj-art-c9f2d671c8f14dd18a347f3071c92f76 |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-c9f2d671c8f14dd18a347f3071c92f762024-12-10T05:32:51ZengPublic Library of Science (PLoS)PLoS ONE1932-62032024-01-01194e029929710.1371/journal.pone.0299297Deep Aramaic: Towards a synthetic data paradigm enabling machine learning in epigraphy.Andrei C AioaneiRegine R Hunziker-RodewaldKonstantin M KleinDominik L MichelsEpigraphy is witnessing a growing integration of artificial intelligence, notably through its subfield of machine learning (ML), especially in tasks like extracting insights from ancient inscriptions. However, scarce labeled data for training ML algorithms severely limits current techniques, especially for ancient scripts like Old Aramaic. Our research pioneers an innovative methodology for generating synthetic training data tailored to Old Aramaic letters. Our pipeline synthesizes photo-realistic Aramaic letter datasets, incorporating textural features, lighting, damage, and augmentations to mimic real-world inscription diversity. Despite minimal real examples, we engineer a dataset of 250 000 training and 25 000 validation images covering the 22 letter classes in the Aramaic alphabet. This comprehensive corpus provides a robust volume of data for training a residual neural network (ResNet) to classify highly degraded Aramaic letters. The ResNet model demonstrates 95% accuracy in classifying real images from the 8th century BCE Hadad statue inscription. Additional experiments validate performance on varying materials and styles, proving effective generalization. Our results validate the model's capabilities in handling diverse real-world scenarios, proving the viability of our synthetic data approach and avoiding the dependence on scarce training data that has constrained epigraphic analysis. Our innovative framework elevates interpretation accuracy on damaged inscriptions, thus enhancing knowledge extraction from these historical resources.https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0299297&type=printable |
| spellingShingle | Andrei C Aioanei Regine R Hunziker-Rodewald Konstantin M Klein Dominik L Michels Deep Aramaic: Towards a synthetic data paradigm enabling machine learning in epigraphy. PLoS ONE |
| title | Deep Aramaic: Towards a synthetic data paradigm enabling machine learning in epigraphy. |
| title_full | Deep Aramaic: Towards a synthetic data paradigm enabling machine learning in epigraphy. |
| title_fullStr | Deep Aramaic: Towards a synthetic data paradigm enabling machine learning in epigraphy. |
| title_full_unstemmed | Deep Aramaic: Towards a synthetic data paradigm enabling machine learning in epigraphy. |
| title_short | Deep Aramaic: Towards a synthetic data paradigm enabling machine learning in epigraphy. |
| title_sort | deep aramaic towards a synthetic data paradigm enabling machine learning in epigraphy |
| url | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0299297&type=printable |
| work_keys_str_mv | AT andreicaioanei deeparamaictowardsasyntheticdataparadigmenablingmachinelearninginepigraphy AT reginerhunzikerrodewald deeparamaictowardsasyntheticdataparadigmenablingmachinelearninginepigraphy AT konstantinmklein deeparamaictowardsasyntheticdataparadigmenablingmachinelearninginepigraphy AT dominiklmichels deeparamaictowardsasyntheticdataparadigmenablingmachinelearninginepigraphy |