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

Ali Alameer; Patrick Degenaar; Kianoush Nazarpour

doi:10.1109/INISTA.2017.8001150

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

Ali Alameer, Patrick Degenaar, Kianoush Nazarpour

School of Biological Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Citations (Scopus)

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 language	Undefined/Unknown
Title of host publication	INnovations in Intelligent SysTems and Applications (INISTA), 2017 IEEE International Conference on
Publisher	Institute of Electrical and Electronics Engineers Inc.
Number of pages	5
ISBN (Electronic)	978-1-5090-5795-5
ISBN (Print)	978-1-5090-5796-2
DOIs	https://doi.org/10.1109/INISTA.2017.8001150
Publication status	Published - 08 Aug 2017

Access to Document

10.1109/INISTA.2017.8001150Licence: Unspecified

https://www.researchgate.net/publication/318978785_Processing_occlusions_using_elastic-net_hierarchical_MAX_model_of_the_visual_cortex

Cite this

@inproceedings{9c76ebd589c64e84918c2753f46caaf4,

title = "Processing occlusions using elastic-net hierarchical MAX model of the visual cortex",

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.",

author = "Ali Alameer and Patrick Degenaar and Kianoush Nazarpour",

year = "2017",

month = aug,

day = "8",

doi = "10.1109/INISTA.2017.8001150",

language = "Undefined/Unknown",

isbn = "978-1-5090-5796-2",

booktitle = "INnovations in Intelligent SysTems and Applications (INISTA), 2017 IEEE International Conference on",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

}

Processing occlusions using elastic-net hierarchical MAX model of the visual cortex. / Alameer, Ali; Degenaar, Patrick; Nazarpour, Kianoush.
INnovations in Intelligent SysTems and Applications (INISTA), 2017 IEEE International Conference on. Institute of Electrical and Electronics Engineers Inc., 2017.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Processing occlusions using elastic-net hierarchical MAX model of the visual cortex

AU - Alameer, Ali

AU - Degenaar, Patrick

AU - Nazarpour, Kianoush

PY - 2017/8/8

Y1 - 2017/8/8

N2 - 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.

AB - 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.

U2 - 10.1109/INISTA.2017.8001150

DO - 10.1109/INISTA.2017.8001150

M3 - Conference contribution

SN - 978-1-5090-5796-2

BT - INnovations in Intelligent SysTems and Applications (INISTA), 2017 IEEE International Conference on

PB - Institute of Electrical and Electronics Engineers Inc.

ER -