For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Image Decomposition by Answer-in-Weights Neural Network
Iren VALOVA Keisuke KAMEYAMA Yukio KOSUGI
IEICE TRANSACTIONS on Information and Systems
Publication Date: 1995/09/25
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Image Processing, Computer Graphics and Pattern Recognition
image decomposition, neural networks, steepest decent method, Hadamard functions,
Full Text: PDF(330.5KB)>>
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.