ICA filters for lighting invariant face recognition

Fortuna, J.; Capson, David W.

doi:10.1109/icpr.2004.1334120

Cited by 7 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PCA and ICA have, for example, been used to recognize people from iris images (Wang and Han 2005) or their faces (Fortuna and Capson 2004). Recent advances in this area include latent variable models, such as Gaussian process latent variable models (GPLVMs) (Lawrence 2005).…”

Section: Related Workmentioning

confidence: 99%

Classifying dynamic objects

et al. 2009

View full text Add to dashboard Cite

For robots operating in real-world environments, the ability to deal with dynamic entities such as humans, animals, vehicles, or other robots is of fundamental importance. The variability of dynamic objects, however, is large in general, which makes it hard to manually design suitable models for their appearance and dynamics. In this paper, we present an unsupervised learning approach to this modelbuilding problem. We describe an exemplar-based model for representing the time-varying appearance of objects in planar laser scans as well as a clustering procedure that builds a set of object classes from given observation sequences. Extensive experiments in real environments demonstrate that our system is able to autonomously learn useful models for, e.g., pedestrians, skaters, or cyclists without being provided with external class information.

show abstract

Section: Related Workmentioning

confidence: 99%

Classifying dynamic objects

et al. 2009

View full text Add to dashboard Cite

show abstract

“…As an alternative to the exemplar-based approach, researchers have applied generic dimensionality reduction techniques in order to deal with high-dimensional and/or dynamic appearance distributions. PCA and ICA have, for example, been used to recognize people from iris images [19] or their faces [20]. Recent advances in this area include Isomap [21] and latent variable models, such as GP-LVM [22].…”

Section: Related Workmentioning

confidence: 99%

Classifying Dynamic Objects: An Unsupervised Learning Approach

Luber¹,

Arras²,

Plagemann³

et al. 2009

Robotics

View full text Add to dashboard Cite

For robots operating in real-world environments, the ability to deal with dynamic entities such as humans, animals, vehicles, or other robots is of fundamental importance. The variability of dynamic objects, however, is large in general, which makes it hard to manually design suitable models for their appearance and dynamics. In this paper, we present an unsupervised learning approach to this model-building problem. We describe an exemplar-based model for representing the time-varying appearance of objects in planar laser scans as well as a clustering procedure that builds a set of object classes from given training sequences. Extensive experiments in real environments demonstrate that our system is able to autonomously learn useful models for, e.g., pedestrians, skaters, or cyclists without being provided with external class information.

show abstract

“…PCA and ICA have, for example, been used to recognize people from iris images [19] or their faces [20]. Recent advances in this area include Isomap [21] and latent variable models, such as GP-LVM [22].…”

Section: Related Workmentioning

confidence: 99%

Classifying Dynamic Objects: An Unsupervised Learning Approach

Luber

Arras

Plagemann

et al. 2008

Robotics: Science and Systems IV

View full text Add to dashboard Cite

Abstract-For robots operating in real-world environments, the ability to deal with dynamic entities such as humans, animals, vehicles, or other robots is of fundamental importance. The variability of dynamic objects, however, is large in general, which makes it hard to manually design suitable models for their appearance and dynamics. In this paper, we present an unsupervised learning approach to this model-building problem. We describe an exemplar-based model for representing the time-varying appearance of objects in planar laser scans as well as a clustering procedure that builds a set of object classes from given training sequences. Extensive experiments in real environments demonstrate that our system is able to autonomously learn useful models for, e.g., pedestrians, skaters, or cyclists without being provided with external class information.

show abstract

ICA filters for lighting invariant face recognition

Cited by 7 publications

References 7 publications

Classifying dynamic objects

Classifying dynamic objects

Classifying Dynamic Objects: An Unsupervised Learning Approach

Classifying Dynamic Objects: An Unsupervised Learning Approach

Contact Info

Product

Resources

About