Title :
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
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;
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
DOI :
10.1109/NNSP.1993.471861
