Sparse approximation of images inspired from the functional architecture of the primary visual areas

Authors:
Sylvain Fischer;Rafael Redondo;Laurent Perrinet;Gabriel Cristóbal
Affiliations:
Instituto de Óptica-CSIC, Madrid, Spain and INCM, UMR, CNRS and Aix-Marseille University, Marseille Cedex, France;Instituto de Óptica-CSIC, Madrid, Spain;INCM, UMR, CNRS and Aix-Marseille University, Marseille Cedex, France;Instituto de Óptica-CSIC, Madrid, Spain
Venue:
EURASIP Journal on Applied Signal Processing
Year:
2007

Citing 18
Cited 5

A Computational Approach to Edge Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Characterization of Signals from Multiscale Edges

IEEE Transactions on Pattern Analysis and Machine Intelligence
Synthetic aperture radar processing by a multiple scale neural system for boundary and surface representation

Neural Networks - Special issue: automatic target recognition
Collinearity and Parallelism are Statistically Significant Second-Order Relations of Complex Cell Responses

Neural Processing Letters
Atomic Decomposition by Basis Pursuit

SIAM Journal on Scientific Computing
Are Edges Incomplete?

International Journal of Computer Vision - Special issue on computer vision research at NEC Research Institute
A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients

International Journal of Computer Vision - Special issue on statistical and computational theories of vision: modeling, learning, sampling and computing, Part I
The Problem of Sparse Image Coding

Journal of Mathematical Imaging and Vision
The Design and Analysis of Efficient Lossless Data Compression Systems

The Design and Analysis of Efficient Lossless Data Compression Systems
Image Compression using an Efficient Edge Cartoon + Texture Model

DCC '02 Proceedings of the Data Compression Conference
Image compression using an edge adapted redundant dictionary and wavelets

Signal Processing - Sparse approximations in signal and image processing
Self-Invertible 2D Log-Gabor Wavelets

International Journal of Computer Vision
Adaptive wavelet thresholding for image denoising and compression

IEEE Transactions on Image Processing
Image denoising using scale mixtures of Gaussians in the wavelet domain

IEEE Transactions on Image Processing
Image decomposition via the combination of sparse representations and a variational approach

IEEE Transactions on Image Processing
The contourlet transform: an efficient directional multiresolution image representation

IEEE Transactions on Image Processing
Sparse overcomplete Gabor wavelet representation based on local competitions

IEEE Transactions on Image Processing
Coding static natural images using spiking event times: do neurons Cooperate?

IEEE Transactions on Neural Networks

Iterated tensor voting and curvature improvement

Signal Processing
Self-Invertible 2D Log-Gabor Wavelets

International Journal of Computer Vision
Multifocus image fusion using the log-Gabor transform and a Multisize Windows technique

Information Fusion
Class specific redundancies in natural images: a theory of extrastriate visual processing

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Role of homeostasis in learning sparse representations

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Several drawbacks of critically sampled wavelets can be solved by overcomplete multiresolution transforms and sparse approximation algorithms. Facing the difficulty to optimize such nonorthogonal and nonlinear transforms, we implement a sparse approximation scheme inspired from the functional architecture of the primary visual cortex. The scheme models simple and complex cell receptive fields through log-Gabor wavelets. The model also incorporates inhibition and facilitation interactions between neighboring cells. Functionally these interactions allow to extract edges and ridges, providing an edge-based approximation of the visual information. The edge coefficients are shown sufficient for closely reconstructing the images, while contour representations by means of chains of edges reduce the information redundancy for approaching image compression. Additionally, the ability to segregate the edges from the noise is employed for image restoration.