The cascade-correlation learning architecture
Advances in neural information processing systems 2
TRAFFIC: recognizing objects using hierarchical reference frame transformations
Advances in neural information processing systems 2
The perception of multiple objects: a connectionist approach
The perception of multiple objects: a connectionist approach
International Journal of Computer Vision
1994 Special Issue: Modeling visual recognition from neurobiological constraints
Neural Networks - Special issue: models of neurodynamics and behavior
Learning Recognition and Segmentation Using the Cresceptron
International Journal of Computer Vision
Robust classification of arbitrary object classes based on hierarchical spatial feature-matching
Machine Vision and Applications
Statistical Language Learning
Distortion Invariant Object Recognition in the Dynamic Link Architecture
IEEE Transactions on Computers
Multidimensional Indexing for Recognizing Visual Shapes
IEEE Transactions on Pattern Analysis and Machine Intelligence
Probabilistic Object Recognition Using Multidimensional Receptive Field Histograms
ICPR '96 Proceedings of the 13th International Conference on Pattern Recognition - Volume 2
Learning to recognize three-dimensional objects
Neural Computation
A Tale of Two Classifiers: SNoW vs. SVM in Visual Recognition
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
A Neural Network Model Generating Invariance for Visual Distance
ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
Proceedings of the 2004 ACM workshop on Visualization and data mining for computer security
| Hi-index | 0.00 |
We have studied some of the design trade-offs governing visual representations based on spatially invariant conjunctive feature detectors, with an emphasis on the susceptibility of such systems to false-positive recognition errors—Malsburg's classical binding problem. We begin by deriving an analytical model that makes explicit how recognition performance is affected by the number of objects that must be distinguished, the number of features included in the representation, the complexity of individual objects, and the clutter load, that is, the amount of visual material in the field of view in which multiple objects must be simultaneously recognized, independent of pose, and without explicit segmentation. Using the domain of text to model object recognition in cluttered scenes, we show that with corrections for the nonuniform probability and nonindependence of text features, the analytical model achieves good fits to measured recognition rates in simulations involving a wide range of clutter loads, word sizes, and feature counts. We then introduce a greedy algorithm for feature learning, derived from the analytical model, which grows a representation by choosing those conjunctive features that are most likely to distinguish objects from the cluttered backgrounds in which they are embedded. We show that the representations produced by this algorithm are compact, decorrelated, and heavily weighted toward features of low conjunctive order. Our results provide a more quantitative basis for understanding when spatially invariant conjunctive features can support unambiguous perception in multiobject scenes, and lead to several insights regarding the properties of visual representations optimized for specific recognition tasks.