Image Decomposition by Answer-in-Weights Neural Network

Iren VALOVA  Keisuke KAMEYAMA  Yukio KOSUGI  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E78-D   No.9   pp.1221-1224
Publication Date: 1995/09/25
Online ISSN: 
DOI: 
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Image Processing, Computer Graphics and Pattern Recognition
Keyword: 
image decomposition,  neural networks,  steepest decent method,  Hadamard functions,  

Full Text: PDF(330.5KB)>>
Buy this Article




Summary: 
We propose an algorithm for image decomposition based on Hadamard functions, realized by answer-in-weights neural network, which has simple architecture and is explored with steepest decent method. This scheme saves memory consumption and it converges fast. Simulations with least mean square (LMS) and absolute mean (AM) errors on a 128128 image converge within 30 training epochs.