Feature detection using spikes: The greedy approach

Perrinet, Laurent

doi:10.1016/j.jphysparis.2005.09.012

Cited by 14 publications

(18 citation statements)

References 30 publications

(37 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Many other applications can also be derived since the ability of coding image features through a reduced set of large transform coefficients makes the transformation suitable for many applications such as image fusion or feature extraction. For image compression but also for general applications the redundancy induced by the overcompleteness could be recovered by deploying sparse approximation algorithms (Perrinet, 2004;Fischer et al, in press). …”

Section: Discussionmentioning

confidence: 99%

Self-Invertible 2D Log-Gabor Wavelets

et al. 2007

Self Cite

View full text Add to dashboard Cite

Abstract. Orthogonal and biorthogonal wavelets became very popular image processing tools but exhibit major drawbacks, namely a poor resolution in orientation and the lack of translation invariance due to aliasing between subbands. Alternative multiresolution transforms which specifically solve these drawbacks have been proposed. These transforms are generally overcomplete and consequently offer large degrees of freedom in their design. At the same time their optimization gets a challenging task. We propose here the construction of log-Gabor wavelet transforms which allow exact reconstruction and strengthen the excellent mathematical properties of the Gabor filters. Two major improvements on the previous Gabor wavelet schemes are proposed: first the highest frequency bands are covered by narrowly localized oriented filters. Secondly, the set of filters cover uniformly the Fourier domain including the highest and lowest frequencies and thus exact reconstruction is achieved using the same filters in both the direct and the inverse transforms (which means that the transform is self-invertible). The present transform not only achieves important mathematical properties, it also follows as much as possible the knowledge on the receptive field properties of the simple cells of the Primary Visual Cortex (V1) and on the statistics of natural images. Compared to the state of the art, the log-Gabor wavelets show excellent ability to segregate the image information (e.g. the contrast edges) from spatially incoherent Gaussian noise by hard thresholding, and then to represent image features through a reduced set of large magnitude coefficients. Such characteristics make the transform a promising tool for processing natural images.

show abstract

Section: Discussionmentioning

confidence: 99%

Self-Invertible 2D Log-Gabor Wavelets

et al. 2007

Self Cite

View full text Add to dashboard Cite

show abstract

“…We will here propose a solution for inverting the forward model that we defined for natural images based on a Bayesian inference framework using feature-matching neurons and spikes as events representing primitive "decisions". In fact, as in numerous optimization problems, a solution is to begin the algorithm with a subset of the problem which is easy to solve, take it into account and then to resume the algorithm in a recursive manner on the transformed observation signal : it's the greedy approach [Perrinet, 2004b]. Following this process and focusing on every single spike, a greedy solution could use recursively two steps: Matching (M) and Pursuit (P).…”

Section: One Solution: Greedy Inference Pursuitmentioning

confidence: 99%

“…However, a problem with Matching Pursuit [Mallat and Zhang, 1993] is that any decision in this recursive scheme is propagated to the following steps and that the algorithm is progressively more prone to detection errors. Thanks to the interpretation of MP in a probabilistic framework [Perrinet, 2004b], we may lower the risk of false detection by explicitly taking into account the variability of image formation in space but also specifically to the knowledge of one source:…”

Section: Handling Uncertain Input and Filtersmentioning

confidence: 99%

Dynamical neural networks: Modeling low-level vision at short latencies

Perrinet

2007

Eur. Phys. J. Spec. Top.

View full text Add to dashboard Cite

Our goal is to understand the dynamics of neural computations in low-level vision. We study how the substrate of this system, that is local biochemical neural processes, could combine to give rise to an efficient and global perception. We will study these neural computations at different scales from the single-cell to the whole visual system to infer generic aspects of the underlying neural code which may help to understand this cognitive ability. In fact, the architecture of cortical areas, such as the Primary Visual Cortex (V1), is massively parallel and we will focus on cortical columns as generic adaptive micro-circuits. To stress on the dynamical aspect of the processing, we will also focus on the transient response, that is during the first milliseconds after the presentation of a stimulus. In a generic model of a visual area, we propose to study the neural code as implementing visual pattern matching, that is as efficiently inverting a known model of image synthesis. A possible solution offered by the architecture of the visual pathways could be to represent at first on the surface of the cortical area how well the prototypical visual features are matched by a combination of inferential mechanisms as ideal observers. We studied the efficiency of this representation by rating the statistics of the output using natural scenes, that is scenes occurring frequently. We show that this may be finally used to provide a behavioral output such as an eye movement. However, constraints specific to the visual system imply that the set of prototypical features is not independent and that the cortical columns should communicate to produce an efficient, sparse solution. We will present efficient algorithms and representations based on the event-based nature of neural computations. By explicitely defining this efficiency, we propose then a simple implementation of Sparse Spike Coding using greedy inference mechanisms but also how the system may adapt in a unsupervised fashion. These computations may be implemented in simple models of neural networks by explicitly setting the lateral connectivity between populations of columns. Using natural scenes, this algorithm provides a model of V1 which exhibit prototypical properties of neural activities in that area. We show simple applications in the field of image processing as a quantitative method to evaluate these different cortical models.

show abstract

“…We will then in a third section pro-pose that this linear information may be optimally coded by a spike list if we apply a point non-linear operation. At least, we will define an improvment over Matching Pursuit (Mallat and Zhang, 1993) by optimizing the efficiency of the ArgMax operator and which finally defines Sparse Spike Coding (Perrinet, 2004(Perrinet, , 2007Perrinet et al, 2002).…”

Section: Introduction: Efficient Neural Representationsmentioning

confidence: 99%

Sparse spike coding : applications of neuroscience to the processing of natural images

Perrinet

2008

Optical and Digital Image Processing

View full text Add to dashboard Cite

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.

show abstract

Feature detection using spikes: The greedy approach

Cited by 14 publications

References 30 publications

Self-Invertible 2D Log-Gabor Wavelets

Self-Invertible 2D Log-Gabor Wavelets

Dynamical neural networks: Modeling low-level vision at short latencies

Sparse spike coding : applications of neuroscience to the processing of natural images

Contact Info

Product

Resources

About