Image generation and inversion based on a probabilistic recurrent neural model

Author

Sonehara, Noboru ; Nakane, Kazunari ; Tokunaga, Yukio

Author_Institution

NTT Human Interface Lab., Kanagawa, Japan

fYear

1993

fDate

6-9 Sep 1993

Firstpage

271

Lastpage

280

Abstract

The iterated function system composed of contraction mappings can generate various intricate images with very few parameters in simple and iterative computations. A recurrent neural model with probabilistically weighted connections is proposed as a nonlinear iterated function system. To find connection weights of the recurrent neural model that generates an approximate version of a given gray scale image, an adaptive function estimation method, using the square error criteria, is proposed. Its coding efficiency is evaluated

Keywords

computer graphics; image coding; iterative methods; probability; recurrent neural nets; adaptive function estimation; coding; contraction mappings; gray scale image; image generation; iterated function system; probabilistic recurrent neural model; probabilistically weighted connections; square error criteria; Discrete cosine transforms; Electronic mail; Humans; Image coding; Image generation; Image processing; Image reconstruction; Image resolution; Inverse problems; Laboratories;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks for Processing [1993] III. Proceedings of the 1993 IEEE-SP Workshop

Conference_Location

Linthicum Heights, MD

Print_ISBN

0-7803-0928-6

Type

conf

DOI

10.1109/NNSP.1993.471861

Filename

471861