Author/Researcher: Yujeong (Erin) Lee

Take a look at the project on Gitlab: https://code.cs.earlham.edu/elee17/capstone-cuneiform-image-processing.

Watch the software demonstration on Youtube: https://youtu.be/XKweV6jdfxs

Read the paper on Google Drive: https://drive.google.com/file/d/1FbfkI6wKPajhWrgkG2fCWU6BwHKeuqrM/view?usp=sharing

Abstract

Ancient Near Eastern cuneiform tablets document one of the earliest writing systems known. Extensive collections of cuneiform tablets are in the process of being digitized by many institutions worldwide in an effort to make the digitized inscriptions available to remote researchers. With an increasing demand for digitization in the museum sector, this project addresses the ineffectiveness of manual image processing and aims to contribute to ancient Near Eastern studies with automated image processing of cuneiform tablets.

Manually, a six-sided tablet is scanned on each side on a flatbed scanner and sent for post-production, in which the images are digitally enhanced and stitched in the form of a “fatcross” using programs like Photoshop. Automation of such image processing will include 1) preparation of the image data, 2) image segmentation with methods like thresholding, and 3) accurate assembly of separate images. This research aims to identify a simple and effective edge detection method and its implementation parameters to automate building a fatcross.

Poster

Software architecture diagram