A Differential Model of the Complex Cell
From MaRDI portal
Abstract: The receptive fields of simple cells in the visual cortex can be understood as linear filters. These filters can be modelled by Gabor functions, or by Gaussian derivatives. Gabor functions can also be combined in an `energy model' of the complex cell response. This paper proposes an alternative model of the complex cell, based on Gaussian derivatives. It is most important to account for the insensitivity of the complex response to small shifts of the image. The new model uses a linear combination of the first few derivative filters, at a single position, to approximate the first derivative filter, at a series of adjacent positions. The maximum response, over all positions, gives a signal that is insensitive to small shifts of the image. This model, unlike previous approaches, is based on the scale space theory of visual processing. In particular, the complex cell is built from filters that respond to the wod differential structure of the image. The computational aspects of the new model are studied in one and two dimensions, using the steerability of the Gaussian derivatives. The response of the model to basic images, such as edges and gratings, is derived formally. The response to natural images is also evaluated, using statistical measures of shift insensitivity. The relevance of the new model to the cortical image representation is discussed.
Recommendations
- A cellular automata model for cell differentiation
- A compartmental reaction-diffusion cell cycle model
- scientific article; zbMATH DE number 1120700
- Multi-scale modelling in cell dynamics
- A structured population model of cell differentiation
- A general model for the dynamics of the cell volume
- scientific article; zbMATH DE number 176944
- A diffusion model for cell polarization with interactions on the membrane
Cites work
- Biophysiologically Plausible Implementations of the Maximum Operation
- Geometrical Computations Explain Projection Patterns of Long-Range Horizontal Connections in Visual Cortex
- scientific article; zbMATH DE number 1983334 (Why is no real title available?)
- scientific article; zbMATH DE number 274379 (Why is no real title available?)
- Image Representation by Complex Cell Responses
- Receptive field families
- Representation of local geometry in the visual system
- Slow Feature Analysis: Unsupervised Learning of Invariances
- The monogenic signal
- The structure of images
Cited in
(14)- Ramp edges, Mach bands, and the functional significance of the simple cell assembly
- Responses of simple cells: Events, interferences, and ambiguities
- Provably scale-covariant continuous hierarchical networks based on scale-normalized differential expressions coupled in cascade
- Equation of motion and general solution for the one-dimensional complex cell response in the signal-tuned approach
- Finite Discrete, Shift-Invariant, Directional Filterbanks for Visual Information Processing, I : Construction
- scientific article; zbMATH DE number 1977120 (Why is no real title available?)
- scientific article; zbMATH DE number 1977126 (Why is no real title available?)
- Image Representation by Complex Cell Responses
- Receptive Field Structures for Recognition
- The many faces of Ocneanu cells
- Orientation selectivity properties for the affine Gaussian derivative and the affine Gabor models for visual receptive fields
- Do the receptive fields in the primary visual cortex span a variability over the degree of elongation of the receptive fields?
- A computational theory of visual receptive fields
- Mathematical model of the simple cells in the visual cortex
This page was built for publication: A Differential Model of the Complex Cell
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3116930)
