IEEE Transactions on Pattern Analysis and Machine Intelligence
The computing neuron
Optical flow estimation: advances and comparisons
ECCV '94 Proceedings of the third European conference on Computer vision (vol. 1)
Implementing a Multi-Model Estimation Method
International Journal of Computer Vision
Variational Methods for Multimodal Image Matching
International Journal of Computer Vision
Robust and fast computation of unbiased intensity derivatives in images
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Biophysiologically plausible implementations of the maximum operation
Neural Computation
Spike-Timing-Dependent Hebbian Plasticity as Temporal Difference Learning
Neural Computation
Vector-valued image regularization with PDE's: a common framework for different applications
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
A Volterra type model for image processing
IEEE Transactions on Image Processing
Hi-index | 0.00 |
In computer or biological vision, computation of vectorial maps of parametric quantities (e.g. feature parameters, 3D or motion cues,..) are of common use in perceptual processes. Defining them using continuous partial differential equations yields highly parallelizable regularization processes allowing to obtain well-defined estimations of these quantities. However these equations have to be sampled on real data and this step is not obvious and may introduce some bias. In order to overcome this caveat, a method, introduced by Raviat and developed by Degond and Mas-Gallic, is based on an integral approximation of the diffusion operator used in regularization mechanisms: it leads to a so-called ''particle'' implementation of such diffusion process. Following this formulation, the present development defines an optimal implementation of such an integral operator with the interesting property that when used on sampled data such as image pixels or 3D data voxels, it provides an unbiased implementation of the corresponding continuous operator without any other approximation. Furthermore, the method is 'automatic' (using symbolic computations) in the sense that given a continuous regularization mechanism, the corresponding (non-linear) discrete filter is derived automatically, as made explicit here. A step ahead, the architecture of the implementation corresponds to what is observed in cortical visual maps, leading to a certain biological plausibility. The present development is illustrated by an experiment of visual motion estimation and another experiment in image denoising.