Browse by author
Lookup NU author(s): Dr Ali Alameer,
Professor Patrick Degenaar,
Professor Kianoush Nazarpour
This is the authors' accepted manuscript of a conference proceedings (inc. abstract) that has been published in its final definitive form by Springer, Cham, 2019.
For re-use rights please refer to the publisher's terms and conditions.
Object recognition is a challenging problem in high-level vision. Models that perform well for the outdoor domain, perform poorly in the indoor domain and the reverse is also true. This is due to the dramatic discrepancies of the global properties of each environment, for instance, backgrounds and lighting conditions. Here, we show that inferring the environment before or during the recognition process can dramatically enhance the recognition performance. We used a combination of deep and shallow models for object and scene recognition, respectively. Also, we used three novel topologies that can provide a trade-off between classification accuracy and decision sensitivity. We achieved a classification accuracy of 97.91%, outperforming the performance of a single GoogLeNet by 13%. In another experiment, we achieved an accuracy of 95% to categorise indoor and outdoor scenes by inference.
Author(s): Alameer A, Degenaar P, Nazarpour K
Publication type: Conference Proceedings (inc. Abstract)
Publication status: Published
Conference Name: Advances in Computer Vision: Proceedings of the 2019 Computer Vision Conference (CVC 2019)
Year of Conference: 2019
Online publication date: 24/04/2019
Acceptance date: 28/11/2018
Date deposited: 11/10/2019
Publisher: Springer, Cham
Library holdings: Search Newcastle University Library for this item
Series Title: Advances in Intelligent Systems and Computing