A neuromorphic model for achromatic and chromatic surface representation of natural images

Hong, Simon; Grossberg, Stephen

doi:10.1016/j.neunet.2004.02.007

Cited by 30 publications

(33 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the present, only few such models are available (e.g. Hong & Grossberg, 2004). Our contribution takes a step towards this direction.…”

Section: Discussionmentioning

confidence: 99%

“…A standard technique is to band-pass filter the visual input over multiple scales, and subsequently adding luminance information to recover absolute luminance levels (e.g. Hong & Grossberg, 2004;Neumann, 1996;Pessoa et al, 1995). We instead propose a multiplexed retinal code, which is generated from contrast responses by modulating ON-cell (OFF-cell) responses with local brightness (darkness) (Fig.…”

Section: Recovering Absolute Levels Of Perceived Luminancementioning

confidence: 99%

“…Filling-in models were also applied to improve the perceived quality of synthetic aperture radar (SAR) images (Grossberg, Mingolla, & Williamson, 1995;Mingolla, Ross, & Grossberg, 1999). But for all that success so far, results from filling-in models with real-world images remain scarce (with the exception of Hong and Grossberg (2004) and Sepp & Neumann (1999)). …”

mentioning

confidence: 99%

“…As a solution, most models addressing brightness perception and image coding, respectively, propose a low-pass or luminance channel, in addition to (often multi-scale) contrast channels (e.g. du Buf & Fischer, 1995;Hong & Grossberg, 2004;Pessoa et al, 1995, but see Arrington, 1996: luminance information is superimposed with filled-in or multi-scale-contrast information to recover absolute luminance levels.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Recovering real-world images from single-scale boundaries with a novel filling-in architecture

Keil

Cristóbal²,

Hansen³

et al. 2005

Neural Networks

View full text Add to dashboard Cite

Filling-in models were successful in predicting psychophysical data for brightness perception. Nevertheless, their suitability for real-world image processing has never been examined. A unified architecture for both predicting psychophysical data and real-world image processing would constitute a powerful theory for early visual information processing. As a first contribution of the present paper, we identified three principal problems with current filling-in architectures, which hamper the goal of having such a unified architecture. To overcome these problems we propose an advance to filling-in theory, called BEATS filling-in, which is based on a novel nonlinear diffusion operator. BEATS filling-in furthermore introduces novel boundary structures. We compare, by means of simulation studies with real-world images, the performance of BEATS filling-in with the recently proposed confidence-based filling-in. As a second contribution we propose a novel mechanism for encoding luminance information in contrast responses ('multiplex contrasts'), which is based on recent neurophysiological findings. Again, by simulations, we show that 'multiplex contrasts' at a single, high-resolution filter scale are sufficient for recovering absolute luminance levels. Hence, 'multiplex contrasts' represent a novel theory addressing how the brain encodes and decodes luminance information. q

show abstract

“…At the present, only few such models are available (e.g. Hong & Grossberg, 2004). Our contribution takes a step towards this direction.…”

Section: Discussionmentioning

confidence: 99%

Section: Recovering Absolute Levels Of Perceived Luminancementioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Recovering real-world images from single-scale boundaries with a novel filling-in architecture

Keil

Cristóbal²,

Hansen³

et al. 2005

Neural Networks

View full text Add to dashboard Cite

show abstract

“…Lighting conditions and surface context dramatically influence color perception. Preprocessing requires discounting the illuminant, perceptual grouping, surface filling-in and anchoring processes that have been simulated by other neural models, including lightness data (e.g., Grossberg & Todorovic 1988;Hong & Grossberg 2004;Mingolla et al 1999;Pessoa et al 1995). The authors' studies of color category learning and naming used inputs that do not represent challenges that autonomous robots would meet in the real world.…”

Section: Realistic Constraints On Brain Color Perception and Categorymentioning

confidence: 99%

language impairment and colour categories

Davidoff¹,

Luzzatti²

2005

Behav Brain Sci

View full text Add to dashboard Cite

show abstract

Double recurrent interaction V1–V2–V4 based neural architecture for color natural scene boundary detection and surface perception

Pernas

Martínez‐Zarzuela

Antón-Rodríguez

et al. 2014

Applied Soft Computing

View full text Add to dashboard Cite

A neuromorphic model for achromatic and chromatic surface representation of natural images

Cited by 30 publications

References 55 publications

Recovering real-world images from single-scale boundaries with a novel filling-in architecture

Recovering real-world images from single-scale boundaries with a novel filling-in architecture

language impairment and colour categories

Double recurrent interaction V1–V2–V4 based neural architecture for color natural scene boundary detection and surface perception

Contact Info

Product

Resources

About