And the Stone Will Speak: Searching for the Missing Text of the Singapore Stone

Description

The Singapore Stone, re-discovered in 1819 at the mouth of the Singapore River, was a sandstone epigraph inscribed with around fifty lines of text in a writing system which has not be found anywhere else in the world, 'hiding' an unknown language. The British blew it up in 1843, to open an access to the area and to build new facilities. After the explosion, three fragments were recovered by Lt. Col. James Low and sent to Calcutta, to be interpreted. After decades, only one of the fragments was returned from India to the Lion City and is currently preserved at the local National Museum. The text of the Singapore Stone, confusely documented in some drawings before its destruction and in the only extant fragment, is still undeciphered and all attempts at interpreting it failed. The writing system looks unique and, therefore, its analysis and, the more, its possible 'reading' are incredibly difficult. Over time, scholars have postulated the connection of the script of the Stone with some possible deciphered writing systems, mainly from Southeast Asia, and a number of languages from the region have been considered plausible candidates for the epigraph. All this, unfortunately, to no avail. My team's current research, conducted in cooperation with computational scholars from Singapore, aims at using methods from the fields of Computer Vision, Artificial Neural Networks, and Deep Learning to reconstruct the missing parts of the inscription of the Singapore Stone, starting from the fragment we have and extending the investigation, potentially, to the whole epigraph. The above-mentioned methods are implemented by using both Python and OpenCV, while digital images of the historical document are enhanced via image-processing methodologies, such as image restoration, thresholding, and edge detection, in order to identify feature points. This process is eminently philological, and the primary goal is not to decipher directly the text of the Stone (which is almost impossible), but to recover the text itself, in its missing parts, providing scholars with more textual materials to perform frequency analysis, segmentation, and pattern recognition, operations which, theoretically, could lead to the decipherment of the epigraph or, at least, to a better understanding of its writing system and its 'internal syntax', in the context of what can be called 'Computational Epigraphy'.

Period	9 Sept 2023
Held at	School of Humanities and Social Sciences
Degree of Recognition	International