Image and brain: the resolution of the imagery debate
Image and brain: the resolution of the imagery debate
Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Dimension reduction by local principal component analysis
Neural Computation
Independent component analysis: algorithms and applications
Neural Networks
Face Image Analysis by Unsupervised Learning
Face Image Analysis by Unsupervised Learning
Mixtures of Local Linear Subspaces for Face Recognition
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Mental Imagery of Faces and Places Activates Corresponding Stiimulus-Specific Brain Regions
Journal of Cognitive Neuroscience
Using Multivariate Statistics (5th Edition)
Using Multivariate Statistics (5th Edition)
Journal of Cognitive Neuroscience
| Hi-index | 0.00 |
The paper describes a computational model of human expert object recognition in terms of pattern recognition algorithms. In particular, we model the process by which people quickly recognize familiar objects seen from familiar viewpoints at both the instance and category level. We propose a sequence of unsupervised pattern recognition algorithms that is consistent with all known biological data. It combines the standard Gabor-filter model of early vision with a novel cluster-based local linear projection model of expert object recognition in the ventral visual stream. This model is shown to be better than standard algorithms at distinguishing between cats and dogs.