Digitizing Handwritten Field Notebooks: the Impacts of Image Pre-Processing on OCR Text Extraction

Summary

This is an abstract from the "SAA 2024: Individual Abstracts" session, at the 89th annual meeting of the Society for American Archaeology.

Although field notebooks are created as a resource for future archaeologists to reference in their research, the labor required to digitize handwritten notes presents a barrier to their incorporation in state-of-the-art computational analyses. In this research, I explore if image pre-processing can improve the accuracy of text extracted from handwritten field notebooks by Optical Character Recognition. I apply image pre-processing to scans of handwritten field notebooks from the 1970s excavations of the Gulkana Site, a pre-contact Northern Dene site in Alaska’s Copper River Basin. These documents contain important data regarding native copper innovation that occurred at the Gulkana Site but the lack of digital spatial data hinders analysis and public interpretation.

This Resource is Part of the Following Collections

• SAA 2024: Individual Abstracts   •
• Society for American Archaeology 89th Annual Meeting, New Orleans, LA (2024)

Keywords

Spatial Coverage

Record Identifiers

Abstract Id(s): 40141.0