Dynamical stability of formation of cortical maps
Dynamic interactions in neural networks
Distortion Invariant Object Recognition in the Dynamic Link Architecture
IEEE Transactions on Computers
Learning to generalize from single examples in the dynamic link architecture
Neural Computation
Eye Tracking in Image Sequences by Competitive Neural Networks
Neural Processing Letters
Deformation theory of dynamic link matching
Neural Computation
Slow feature analysis: unsupervised learning of invariances
Neural Computation
Proceedings of the 23rd DAGM-Symposium on Pattern Recognition
Matching of medical images by self-organizing neural networks
Pattern Recognition Letters
Dynamic Trees for Unsupervised Segmentation and Matching of Image Regions
IEEE Transactions on Pattern Analysis and Machine Intelligence
Journal of Cognitive Neuroscience
A feature-binding model with localized excitations
Neurocomputing
Face recognition system using accurate and rapid estimation of facial position and scale
AVBPA'03 Proceedings of the 4th international conference on Audio- and video-based biometric person authentication
Hi-index | 0.00 |
When recognizing patterns or objects, our visual system can easily separate what kind of pattern is seen and where (location and orientation) it is seen. Neural networks as pattern recognizers can deal well with noisy input patterns, but have difficulties when confronted with the large variety of possible geometric transformations of an object. We propose a flexible neural mechanism for invariant recognition based on correlated neuronal activity and the self-organization of dynamic links. The system can deal in parallel with different kinds of invariances such as translation, rotation, mirror-reflection, and distortion. It is shown analytically that parts of the neuronal activity equations can be replaced by a faster, but functionally equivalent, algorithmic approach. We derive a measure based on the correlation of activity which allows an unsupervised decision of whether a given input pattern matches with a stored model pattern (''what''-part). At the same time, the dynamic links specify a flexible mapping between input and model (''where''-part). In simulations, the system is applied to both artificial input data and grey level images of real objects.