CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 12 - Volume 12
Object Recognition with Features Inspired by Visual Cortex
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Density Estimation by Mixture Models with Smoothing Priors
Neural Computation
Multiclass Object Recognition with Sparse, Localized Features
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Representing shape with a spatial pyramid kernel
Proceedings of the 6th ACM international conference on Image and video retrieval
An analysis of the elastic net approach to the traveling salesman problem
Neural Computation
The Pascal Visual Object Classes (VOC) Challenge
International Journal of Computer Vision
An analytic distance metric for Gaussian mixture models with application in image retrieval
ICANN'05 Proceedings of the 15th international conference on Artificial neural networks: formal models and their applications - Volume Part II
Differential priors for elastic nets
IDEAL'05 Proceedings of the 6th international conference on Intelligent Data Engineering and Automated Learning
Hi-index | 0.00 |
In this paper we use the Elastic Net (EN) [9] as a visual category representation in feature space. We do this by training the EN on the high dimensional Pyramid Histogram of Visual Words (PHOW) features [2] often used in modern visual categorisation. By employing the topography preserving properties of the EN we visualise the features and draw some novel conclusions. We demonstrate how the EN can also be used as a Region of Interest detector [1]. Finally, inspired by biological vision we propose a new Visual Categorisation scheme that uses ENs as visual category representations. Our method shows promising results when tested on the Caltech101 [12] data set with several interesting future directions.