Virtual Retina: A biological retina model and simulator, with contrast gain control

Wohrer, Adrien; Kornprobst, Pierre

doi:10.1007/s10827-008-0108-4

Cited by 110 publications

(132 citation statements)

References 72 publications

Supporting

Mentioning

131

Contrasting

Order By: Relevance

“…SPAN learning method is based on temporal coding, i.e., information is coded into the precise time of the spikes. Using the VR [19], it was possible to spike encode the digit images and classify the generated spike patterns efficiently. It is noted that the neurons are trained to produce the desired spike sequence in response to their class and not to fire for other classes.…”

Section: Discussionmentioning

confidence: 99%

“…It transforms a video input into spike patterns [19]. The VR consists of three stages of processing layers that correspond to different layers of the retina, namely the Outer Plexiform Layer (OPL), Contrast Gain Control (CGC) and the Ganglion layer (GL).…”

Section: Image To Spike Codingmentioning

confidence: 99%

“…We use 200 sample images per digit (a total of 2000 images) for training and the network is tested on different 200 images per digit. Each sample digit is converted into spike pattern using the Virtual Retina [19]. The produced spike pattern consists of 784 spike trains.…”

Section: Description Of the Datamentioning

confidence: 99%

“…The first stage in the learning process is to convert the images into spike patterns. The conversion is done using the Virtual Retina [19] -a simulator that transforms image/video into pattern of spike trains. The generated patterns are used to train a single layer of SPANs for classification.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Evaluating SPAN Incremental Learning for Handwritten Digit Recognition

Mohemmed

Kasabov

2012

Neural Information Processing

View full text Add to dashboard Cite

In a previous work [12,11], the authors proposed SPAN: a learning algorithm based on temporal coding for Spiking Neural Network (SNN). The algorithm trains a neuron to associate target spike patterns to input spatio-temporal spike patterns. In this paper we present the details of experiment to evaluate the feasibility of SPAN learning on a real-world dataset: classifying images of handwritten digits. As spike encoding is an important issue in using SNN for practical applications, we discuss few methods for image conversion to spike patterns. The experiment yields encouraging results to consider the SPAN learning for practical temporal pattern recognition applications. Abstract. In a previous work [12,11], the authors proposed SPAN: a learning algorithm based on temporal coding for Spiking Neural Network (SNN). The algorithm trains a neuron to associate target spike patterns to input spatio-temporal spike patterns. In this paper we present the details of experiment to evaluate the feasibility of SPAN learning on a real-world dataset: classifying images of handwritten digits. As spike encoding is an important issue in using SNN for practical applications, we discuss few methods for image conversion to spike patterns. The experiment yields encouraging results to consider the SPAN learning for practical temporal pattern recognition applications.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Image To Spike Codingmentioning

confidence: 99%

Section: Description Of the Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Evaluating SPAN Incremental Learning for Handwritten Digit Recognition

Mohemmed

Kasabov

2012

Neural Information Processing

View full text Add to dashboard Cite

show abstract

“…Although preventive treatments exist, there is no treatment method for complete vision loss caused by retinal diseases such as age-related macular degeneration, retinal detachment, and retinitis pigmentosa, which lead to photoreceptor loss [1][2][3]. In recent years, by overcoming this handicap, to create useful vision, many studies have been started to develop artificial vision systems (or visual prostheses) that electrically stimulate the remaining retinal ganglion cells [1,[4][5][6][7][8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

Spatiotemporal realization of an artificial retina model and performance evaluation through ISI- and spike count-based image reconstruction methods

Karagöz¹,

Özden²

2014

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Development of an artificial retina model that can mimic the biologic retina is a highly challenging task and this task is an important step in the development of a visual prosthesis. The receptive field structure of the retina layer is usually modeled as a 2D difference of Gaussian (DOG) filter profile. In the present study, as a different approach, a retina model including a 3D 2-stage DOG filter (3D-ADOG) that has an adaptively changing bandwidth with respect to the local image statistic is developed. Using this modeling, the adaptive image processing of the retina can be realized. The contribution of the developed model in terms of the image quality is evaluated via simulation studies using test images. The first simulation results, including only the spike count-based reconstruction for a test video sequence, were previously published. In this study, in addition to the spike count-based reconstruction, the interspike interval measure is also used in the simulation study. The reconstruction results are compared using the statistical parameters of the mean squared error (MSE), universal quality index (UQI), and histogram similarity ratio (HSR), which characterize the image likelihood. To evaluate the performance of the model versus time, time-dependent changes in the MSE, HSR, and UQI parameters are obtained and compared to the standard model. From these results, it is concluded that the 3D-ADOG filter-based retina model preserves the spatial details of the image and produces a larger number of different gray tone levels, which are important for the visual perception of an image, in comparison with the well-known classical DOG filter-based retina model. The retina implant systems based on this model can provide better visual perception for implant recipients.

show abstract

Retinal Processing: From Biology to Models and Applications

Alleysson

Guyader

2015

Biologically Inspired Computer Vision

View full text Add to dashboard Cite

Virtual Retina: A biological retina model and simulator, with contrast gain control

Cited by 110 publications

References 72 publications

Evaluating SPAN Incremental Learning for Handwritten Digit Recognition

Evaluating SPAN Incremental Learning for Handwritten Digit Recognition

Spatiotemporal realization of an artificial retina model and performance evaluation through ISI- and spike count-based image reconstruction methods

Retinal Processing: From Biology to Models and Applications

Contact Info

Product

Resources

About