Computer vision challenge for the cuneiform script

The current display system used at CDLI requires that a user reads a text to absorb visual and text information simultaneously, and to interpret the mapping between them, since image and transliteration are shown side by side (example: https://cdli.ucla.edu/P315663). Experts in cuneiform studies are usually able to discern this mapping only for their areas of expertise; non-experts and informal learners, on the other hand, have no direct means of affiliating image and annotation content. With the advent of machine learning techniques, this text-image hyperlink concern can now be addressed. This would involve building models using state of the art computer vision techniques specifically trained over a large dataset with annotated ground truth to understand the underlying structure in the tablet images so as to optimally perform image segmentation, character detection and recognition. The goal of the project involves developing machine learning models:

1. That ingest cuneiform text and image to generate segments equivalent to the number of lines of transliteration.
2. Detect and recognize cuneiform characters to generate transliterations directly from the image.