Image Compression and Regeneration by Nonlinear Associative Silicon Retina
Summary :
Threre are two types of nonlinear associative silicon retinas. One is a sparse Hopfield type neural network which is called a H-type retina and the other is its dual network which is called a DH-type retina. The input information sequences of H-type and HD-type retinas are given by nodes and links as voltages and currents respectively. The error correcting capacity (minimum basin of attraction) of H-type and DH-type retinas is decided by the minimum numbers of links of cutset and loop respectively. The operation principle of the regeneration is based on the voltage or current distribution of the neural field. The most important nonlinear operation in the retinas is a dynamic quantization to decide the binary value of each neuron output from the neighbor value. Also, the edge is emphasized by a line-process. The rates of compression of H-type and DH-type retinas used in the simulation are 1/8 and (2/3)
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E75-A No.5 pp.586-594
- Publication Date
- 1992/05/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Special Section PAPER (Special Section on Nonlinear Dynamics--Adaptive, Learning and Neural Systems--)
- Category
- Neural Systems
Authors
Mamoru TANAKA
Yoshinori NAKAMURA
Munemitsu IKEGAMI
Kikufumi KANDA
Taizou HATTORI
Yasutami CHIGUSA
Hikaru MIZUTANI
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Mamoru TANAKA, Yoshinori NAKAMURA, Munemitsu IKEGAMI, Kikufumi KANDA, Taizou HATTORI, Yasutami CHIGUSA, Hikaru MIZUTANI, "Image Compression and Regeneration by Nonlinear Associative Silicon Retina" in IEICE TRANSACTIONS on Fundamentals,
vol. E75-A, no. 5, pp. 586-594, May 1992, doi: .
Abstract: Threre are two types of nonlinear associative silicon retinas. One is a sparse Hopfield type neural network which is called a H-type retina and the other is its dual network which is called a DH-type retina. The input information sequences of H-type and HD-type retinas are given by nodes and links as voltages and currents respectively. The error correcting capacity (minimum basin of attraction) of H-type and DH-type retinas is decided by the minimum numbers of links of cutset and loop respectively. The operation principle of the regeneration is based on the voltage or current distribution of the neural field. The most important nonlinear operation in the retinas is a dynamic quantization to decide the binary value of each neuron output from the neighbor value. Also, the edge is emphasized by a line-process. The rates of compression of H-type and DH-type retinas used in the simulation are 1/8 and (2/3)
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e75-a_5_586/_p
Copy
@ARTICLE{e75-a_5_586,
author={Mamoru TANAKA, Yoshinori NAKAMURA, Munemitsu IKEGAMI, Kikufumi KANDA, Taizou HATTORI, Yasutami CHIGUSA, Hikaru MIZUTANI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Image Compression and Regeneration by Nonlinear Associative Silicon Retina},
year={1992},
volume={E75-A},
number={5},
pages={586-594},
abstract={Threre are two types of nonlinear associative silicon retinas. One is a sparse Hopfield type neural network which is called a H-type retina and the other is its dual network which is called a DH-type retina. The input information sequences of H-type and HD-type retinas are given by nodes and links as voltages and currents respectively. The error correcting capacity (minimum basin of attraction) of H-type and DH-type retinas is decided by the minimum numbers of links of cutset and loop respectively. The operation principle of the regeneration is based on the voltage or current distribution of the neural field. The most important nonlinear operation in the retinas is a dynamic quantization to decide the binary value of each neuron output from the neighbor value. Also, the edge is emphasized by a line-process. The rates of compression of H-type and DH-type retinas used in the simulation are 1/8 and (2/3)
keywords={},
doi={},
ISSN={},
month={May},}
Copy
TY - JOUR
TI - Image Compression and Regeneration by Nonlinear Associative Silicon Retina
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 586
EP - 594
AU - Mamoru TANAKA
AU - Yoshinori NAKAMURA
AU - Munemitsu IKEGAMI
AU - Kikufumi KANDA
AU - Taizou HATTORI
AU - Yasutami CHIGUSA
AU - Hikaru MIZUTANI
PY - 1992
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E75-A
IS - 5
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - May 1992
AB - Threre are two types of nonlinear associative silicon retinas. One is a sparse Hopfield type neural network which is called a H-type retina and the other is its dual network which is called a DH-type retina. The input information sequences of H-type and HD-type retinas are given by nodes and links as voltages and currents respectively. The error correcting capacity (minimum basin of attraction) of H-type and DH-type retinas is decided by the minimum numbers of links of cutset and loop respectively. The operation principle of the regeneration is based on the voltage or current distribution of the neural field. The most important nonlinear operation in the retinas is a dynamic quantization to decide the binary value of each neuron output from the neighbor value. Also, the edge is emphasized by a line-process. The rates of compression of H-type and DH-type retinas used in the simulation are 1/8 and (2/3)
ER -
English
