Sparse Approximation of Images Inspired from the Functional Architecture of the Primary Visual Areas
- 1.1k Downloads
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.
KeywordsApproximation Algorithm Visual Cortex Receptive Field Approximation Scheme Image Compression
- 18.Hansen T, Sepp W, Neumann H: Recurrent long-range interactions in early vision. In Emergent Neural Computational Architectures Based on Neuroscience, LNAI. Volume 2036. Edited by: Wermter S, Austin J, Willshaw D. Springer, Heidelberg, Germany; 2001:127–138. 10.1007/3-540-44597-8_9CrossRefGoogle Scholar
- 22.Coifman RR, Donoho D: Translation-invariant de-noising. In Wavelets and Statistics, Lecture Notes in Statistics. Volume 103. Edited by: Antoniadis A, Oppenheim G. Springer, New York, NY, USA; 1995:125–150. 10.1007/978-1-4612-2544-7_9Google Scholar
- 23.Fischer S, Sroubek F, Perrinet L, Redondo R, Cristóbal G: Self-invertible 2D log-Gabor wavelets. International Journal of Computer Vision, to appearGoogle Scholar
- 33.Rust BW, Rushmeier HE: A new representation of the contrast sensitivity function for human vision. In Proceedings of the International Conference on Imaging Science, Systems, and Technology (CISST '97), June 1997, Las Vegas, Nev, USA Edited by: Arabnia HR. 1–15.Google Scholar
- 39.Kovesi P: Phase congruency detects corners and edges. Proceedings of the 7th International Conference on Digital Image Computing: Techniques and Applications (DICTA '03), December 2003, Sydney, NSW, Australia 309–318.Google Scholar
- 40.Hubel D: Eye, Brain, and Vision, Scientific American Library Series. W. H. Freeman, New York, NY, USA; 1988.Google Scholar
- 43.Redondo R, Cristóbal G: Lossless chain coder for gray edge images. Proceedings of IEEE International Conference on Image Processing (ICIP '03), September 2003, Barcelona, Spain 2: 201–204.Google Scholar
- 45.Howard GP: The design and analysis of efficient lossless data compression systems. In Tech. Rep. CS-93-28. Department of Computer Science, Brown University, Providence, RI, USA; 1993.Google Scholar
- 47.Fischer S: New contributions in overcomplete image representations inspired from the functional architecture of the primary visual cortex, Ph.D. thesis. Technical University Madrid High Technical School of Telecommunication Engineering, Department of Electronic Engineering, Spain; 2007.Google Scholar
This article is published under license to BioMed Central Ltd. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.