Work

Automated Digitization with Python

Year: 2025

Type: article

Abstract: The 'extraction' script can be used to extract tabular data from a set of scanned documents with multiple pages. The user is able to choose which page to select and which not skip. The user can also choose the area of a page that needs to be extracted. The extraction outputs are saved as excel sheets. The 'mapping_cleaning' script can be used to combine all the extracted data into one master sheet and clean the data in order to make it usable for further use.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.16941840

Authors: Sharar, Shihab, Chilukuri, Lakshmi Sowjanya, Jolly, Mintumol

Language: English

Topic: Handwritten Text Recognition Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7081571886

FWCI:

Cites:

Cited by:

Related to: