Processing occlusions using elastic-net hierarchical MAX model of the visual cortex

Alameer, A ORCID: https://orcid.org/0000-0002-7969-3609, Degenaar, P and Nazarpour, K 2017, Processing occlusions using elastic-net hierarchical MAX model of the visual cortex , in: 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA), 03-05 Jul 2017, Gdynia, Poland.

Full text not available from this repository.

Abstract

Humans can recognise objects under partial occlusion. Machine-based approaches cannot reliably recognise objects and scenes in the presence of occlusion. This paper investigates the use of the elastic net hierarchical MAX (En-HMAX) model to handle occlusions. Our experiments show that the En-HMAX model achieves an accuracy of ~70%, when ~50% artificial occlusions are applied to the centre of the visual object-field. Furthermore, when the same percentage of occlusion is applied to the peripheral, the model reports higher accuracies. A similar degree of robustness has been observed when recognising scenes. The results suggest that cortex-like models, such as the En-HMAX are reliable for solving the occlusion challenge.

Item Type:	Conference or Workshop Item (Paper)
Journal or Publication Title:	INnovations in Intelligent SysTems and Applications (INISTA), 2017 IEEE International Conference on
Publisher:	IEEE
Depositing User:	A Alameer
Date Deposited:	09 Jun 2022 15:00
Last Modified:	13 Jun 2022 11:55
URI:	http://usir.salford.ac.uk/id/eprint/63751

Actions (login required)

Edit record (repository staff only)