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: NAIK, Nitin, JENKINS, Paul, GRACE, Paul, YANG, Longzhi and PRAJAPAT, Shaligram, (eds.) Advances in Computational Intelligence Systems. Contributions Presented at The 22nd UK Workshop on Computational Intelligence (UKCI 2023), September 6-8, 2023, Birmingham, UK. Advances in Intelligent Systems and Computing (1453). Cham, Springer, 170-181.

Preview

PDF 2023_ukci_object_detection_in_archival_documents_with_hil.pdf - Accepted Version Creative Commons Attribution. Download (12MB) | Preview

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:	Series ISSN: 2194-5365
Identification Number:	https://doi.org/10.1007/978-3-031-47508-5_14
Page Range:	170-181
SWORD Depositor:	Symplectic Elements
Depositing User:	Symplectic Elements
Date Deposited:	12 Sep 2023 16:05
Last Modified:	05 Feb 2024 13:45
URI:	https://shura.shu.ac.uk/id/eprint/32356

Actions (login required)

View Item

Downloads

Publication Metrics