Sparse Spike Coding : applications of Neuroscience to the processing of natural images

TL;DR

This paper explores a biologically inspired sparse spike coding framework for natural image processing, emphasizing efficiency and neural plausibility, and introduces a Competition Optimized Matching Pursuit algorithm to enhance coding performance.

Contribution

It presents a novel sparse spike coding model inspired by neuroscience, applying it to natural images and optimizing efficiency through lateral interactions and a new matching pursuit variant.

Findings

Efficient neural coding of natural images demonstrated

Sparse coding improves compression and reconstruction quality

Interdisciplinary approach bridges neuroscience and image processing

Abstract

If modern computers are sometimes superior to humans in some specialized tasks such as playing chess or browsing a large database, they can't beat the efficiency of biological vision for such simple tasks as recognizing and following an object in a complex cluttered background. We present in this paper our attempt at outlining the dynamical, parallel and event-based representation for vision in the architecture of the central nervous system. We will illustrate this on static natural images by showing that in a signal matching framework, a L/LN (linear/non-linear) cascade may efficiently transform a sensory signal into a neural spiking signal and we will apply this framework to a model retina. However, this code gets redundant when using an over-complete basis as is necessary for modeling the primary visual cortex: we therefore optimize the efficiency cost by increasing the sparseness of the code. This is implemented by propagating and canceling redundant information using lateral interactions. We compare the efficiency of this representation in terms of compression as the reconstruction quality as a function of the coding length. This will correspond to a modification of the Matching Pursuit algorithm where the ArgMax function is optimized for competition, or Competition Optimized Matching Pursuit (COMP). We will in particular focus on bridging neuroscience and image processing and on the advantages of such an interdisciplinary approach.