Error-Diffusion Binarization for Neural Networks

Granger, André; Galstyan, T. V.; Lessard, Roger A.

doi:10.1007/978-1-4757-9250-8_85

Cited by 1 publication

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been shown that the error diffusion is an effective way to binarize stationary gray level images for their utilization as input vectors of neural networks [3]. We show in the present work that it might provide advantages as better feature extraction of the common features and fast learning convergence of neural networks even under varying illumination ofinput images during the learning process.…”

mentioning

confidence: 89%

“…Thus, there is a necessity of a reliable binarization technique. It has been shown that error diffusion is an effective way to binarize grayscale images for their utilization as input vectors for neural networks [3]. The purpose of our work is the demonstration of advantages of error diffusion technique over the direct binarization when input image intensity changes during the learning process.…”

Section: Introductionmentioning

confidence: 98%

See 1 more Smart Citation

<title>Optimal binarization of input images for holographic neural networks</title>

Boulanov¹,

Galstian²,

Lessard³

2000

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

The optical implementation of neural networks using volume holograms for weighted interconnections requires stable phase relation between input channels. This is particularly important for images with variable illumination. One way to solve this problem is to use binary inputs. The simplest binarization is the direct quantization, but this method has a number of disadvantages. Error diffusion algorithm is more robust under variable illumination since it keeps the original image characteristics.Testing the abilities of error diffusion to process gray level images, we simulated an adaptive neuron unit that has been optically implemented for experiment [1,2]. It has been shown that the error diffusion is an effective way to binarize stationary gray level images for their utilization as input vectors of neural networks [3]. We show in the present work that it might provide advantages as better feature extraction of the common features and fast learning convergence of neural networks even under varying illumination ofinput images during the learning process.

show abstract

mentioning

confidence: 89%

Section: Introductionmentioning

confidence: 98%