New Zealand Journal of Agricultural Research abstracts
A model for image categorisation based on a biological visual
mechanism
He Dongjian
Shao Junming*
Gen Nan
College of Information Engineering
Northwest A&F University
Yangling, Shaanxi, 712100
China
Yang Qinli
College of Resources and Environment
Northwest A&F University
Yangling, Shaanxi, 712100
China
*Author for correspondence: xinyuanwo@yahoo.com.cn
Abstract For integrating a visual
attention mechanism and
object recognition in the visual cortex we propose a novel
biologically-motivated computational model for image categorisation. We
first extract the focus of attention using an image-driven, bottom-up
attention model and then adjust it according to the principles of whole
effect and centre preference. After that, we obtain the region of
interest, depending on the characteristics of object spatial proximity
and object similarity. Based on this we compute a set of position- and
scale-invariant C2 features and finally pool them into the standard
classifier to achieve image categorisation. We test our model on an
image database used in SIMPLIcity. The results suggest that our model
can not only classify images effectively under various complex
“clutters” but also that it needs only a few training samples.
Keywords image categorisation; region of
interest; visual
attention; visual cortex
A07092; Online publication date 25 January 2008; Received and
accepted 10 August 2007
New Zealand Journal of Agricultural Research, 2007, Vol. 50:
781–787
0028–8233/07/5005–0781 © The Royal Society of New Zealand 2007
PDF file of entire paper: Print-quality
(1319K) | screen-quality (550K)
This year's abstracts |
Journal home page |
All abstracts |
Publishing home page
