Segmenting Dead Sea Scroll Fragments for a Scientific Image Set

TL;DR

This paper introduces a specialized four-step segmentation pipeline for Dead Sea Scroll fragments, overcoming unique image challenges, and provides a new dataset for benchmarking and advancing segmentation methods in manuscript analysis.

Contribution

A novel multi-step segmentation pipeline tailored for complex manuscript images and a publicly available dataset with ground truth annotations for evaluation.

Findings

Pipeline effectively isolates fragments despite challenging backgrounds.

Dataset enables reliable evaluation of segmentation methods.

Qualitative and quantitative assessments demonstrate pipeline's robustness.

Abstract

This paper presents a customized pipeline for segmenting manuscript fragments from images curated by the Israel Antiquities Authority (IAA). The images present challenges for standard segmentation methods due to the presence of the ruler, color, and plate number bars, as well as a black background that resembles the ink and varying backing substrates. The proposed pipeline, consisting of four steps, addresses these challenges by isolating and solving each difficulty using custom tailored methods. Further, the usage of a multi-step pipeline will surely be helpful from a conceptual standpoint for other image segmentation projects that encounter problems that have proven intractable when applying any of the more commonly used segmentation techniques. In addition, we create a dataset with bar detection and fragment segmentation ground truth and evaluate the pipeline steps qualitatively and quantitatively on it. This dataset is publicly available to support the development of the field. It aims to address the lack of standard sets of fragment images and evaluation metrics and enable researchers to evaluate their methods in a reliable and reproducible manner.