Object Detection in Heritage Archives using a Human-in-Loop Concept

KASTURI, Surya, SHENFIELD, Alex, ROAST, Chris, LE PAGE, Danny and BROOME, Alice (2024). Object Detection in Heritage Archives using a Human-in-Loop Concept. In: Proceedings of the 22nd UK Workshop on Computational Intelligence. Advances in Intelligent Systems and Computing . Springer.

PDF (RRS OA policy applies, make available on publication) 2023_ukci_object_detection_in_archival_documents_with_hil.pdf - Accepted Version Restricted to Repository staff only Creative Commons Attribution. Download (12MB)

Abstract

The use of object detection has become common within the area of computer vision and has been considered essential for a numerous applications. Currently, the field of object detection has undergone significant development and can be broadly classified into two categories: traditional machine learning methods that employ diverse computer vision techniques, and deep learning methods. This paper proposes a methodology that incorporates the human-in-loop feedback concept to enhance the deep learning object detection capabilities of pre-trained models. These Deep Learning models were developed using a custom humanities and social science dataset that was obtained from the British Online Archives collections database.

Item Type:	Book Section
Additional Information:	Due to be published 22 Jan 2024 Series ISSN: 2194-5365 UKCI the 22nd UK Workshop on Computational Intelligence, Aston University, 6-8 September 2023.
SWORD Depositor:	Symplectic Elements
Depositing User:	Symplectic Elements
Date Deposited:	12 Sep 2023 16:05
Last Modified:	26 Sep 2023 12:59
URI:	https://shura.shu.ac.uk/id/eprint/32356

Actions (login required)

View Item

Downloads

Publication Metrics