作者: Kaneswaran Anantharajah , ZongYuan Ge , Chris McCool , Simon Denman , Clinton Fookes
DOI: 10.1109/WACV.2014.6836084
关键词:
摘要: Object classification is plagued by the issue of session variation. Session variation describes any that makes one instance an object look different to another, for due pose or illumination Recent work in challenging task face verification has shown variability modelling provides a mechanism overcome some these limitations. However, computer vision purposes, it only been applied limited setting verification. In this paper we propose local region based intersession (ISV) approach, and apply real-world data. We approach so variations can be modelled, termed Local ISV. then demonstrate efficacy technique on fish image database which includes images taken underwater, providing significant variations. This ISV relative performance improvement of, average, 23% MOBIO, Multi-PIE SCface databases. It also 35% our dataset.