Using NARX neural network based load prediction to improve scheduling decision in grid environments
In grid environment, applications are in active competition with unknown background
workloads introduced by other users. To achieve good performance, performance models …
workloads introduced by other users. To achieve good performance, performance models …
Image enhancement by high-order Gaussian derivative filters simulating non-classical receptive fields in the human visual system
The non-linearity exhibited by the non-classical receptive field in human visual system has
been combined with the linear classical receptive field model. This enables us to construct …
been combined with the linear classical receptive field model. This enables us to construct …
An image representation of infrastructure based on non-classical receptive field
H Wei, B Lang, QS Zuo - Soft Computing, 2014 - Springer
Biological vision systems have become highly optimized over millions of years of evolution,
developing complex neural structures to represent and process stimuli. Moreover, biological …
developing complex neural structures to represent and process stimuli. Moreover, biological …
A biologically inspired neurocomputing circuit for image representation
H Wei, Q Zuo - Neurocomputing, 2015 - Elsevier
Biological vision systems have evolved over millions of years, resulting in complex neural
structures for representation and processing of stimuli. Moreover, biological visual systems …
structures for representation and processing of stimuli. Moreover, biological visual systems …
A weighted sum of multi-scale Gaussians generates new near-ideal interpolation functions
S Sarkar, K Ghosh, K Bhaumik - 2005 IEEE Engineering in …, 2006 - ieeexplore.ieee.org
Interpolation is a very important technique in medical image processing. Of the different
generations of interpolation kernels, the one using combinations of Gaussians and its partial …
generations of interpolation kernels, the one using combinations of Gaussians and its partial …
A new silicon retina model and its advantages
A new model of silicon retina based on the receptive field structure of retinal ganglion cells
has been proposed. Unlike previous neuromorphic models, the proposed model directly …
has been proposed. Unlike previous neuromorphic models, the proposed model directly …
A new multi-scale Gaussian interpolator that models the blind spot in human eye
The" filling-in" mechanism of the blind spot in human retina has been modeled based on a
possible response function for the non-classical receptive field of retinal ganglion cells. The …
possible response function for the non-classical receptive field of retinal ganglion cells. The …
A retina-inspired neurocomputing circuit for image representation
H Wei, Q Zuo, B Lang - … : 12th International Work-Conference on Artificial …, 2013 - Springer
Biological vision systems have become highly optimized over millions of years of evolution,
developing complex neural structures to represent and process stimuli. Moreover, biological …
developing complex neural structures to represent and process stimuli. Moreover, biological …
Exploration architecturale pour la conception d'un système sur puce de vision robotique, adéquation algorithme-architecture d'un système embarqué temps-réel
T Lefebvre - 2012 - theses.hal.science
La problématique de cette thèse se tient à l'interface des domaines scientifiques de
l'adéquation algorithme architecture, des systèmes de vision bio-inspirée en robotique …
l'adéquation algorithme architecture, des systèmes de vision bio-inspirée en robotique …
A Retinomorphic Sensor Network for Image Preprocessing
The mammalian retina is actually an intelligent sensor network. It is capable of extracting
very rich edge information in the cortex, from the image falling on it, before transferring the …
very rich edge information in the cortex, from the image falling on it, before transferring the …