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

Ali Alameer, Patrick Degenaar, Kianoush Nazarpour

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.
Original languageEnglish
Title of host publication2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages163-167
Number of pages5
ISBN (Electronic)978-1-5090-5795-5
ISBN (Print)978-1-5090-5796-2
DOIs
Publication statusPublished - 8 Aug 2017
Event2017 IEEE International Conference on INovations in Intelligent SysTems and Applications - Gdynia, Poland
Duration: 3 Jul 20175 Jul 2017
http://inista.org/inista17/index.php

Conference

Conference2017 IEEE International Conference on INovations in Intelligent SysTems and Applications
Abbreviated titleINISTA 2017
Country/TerritoryPoland
CityGdynia
Period3/07/175/07/17
Internet address

Fingerprint

Dive into the research topics of 'Processing occlusions using elastic-net hierarchical MAX model of the visual cortex'. Together they form a unique fingerprint.

Cite this