Presentation 1999/12/11
A Study of Lossless Compression of Continous Tone Images by Multi Layer Perceptron
Tetsuro KUGE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A method of loss-less compression of continuous tone images, using two dimensional prediction by multi layer perceptron and adaptive arithmetic coding, is proposed. The predictor is trained by the BP method aming to predict the value of the target pixel using neighboring pixels. Also, a discussion in relation to the likewood method, Laplace distribution on the images, and the loss-function of L1-norm and several experimental results are shown in comparing with the conventional JPEG-LS method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) loss-less compression / MLP / adaptive arithmetic coding / L1-norm / BP algorithm / Laplace dislribution
Paper # NC99-68
Date of Issue

Conference Information
Committee NC
Conference Date 1999/12/11(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study of Lossless Compression of Continous Tone Images by Multi Layer Perceptron
Sub Title (in English)
Keyword(1) loss-less compression
Keyword(2) MLP
Keyword(3) adaptive arithmetic coding
Keyword(4) L1-norm
Keyword(5) BP algorithm
Keyword(6) Laplace dislribution
1st Author's Name Tetsuro KUGE
1st Author's Affiliation Japan Broadcasting Corporation (NHK) Multimedia Development Dept. Digital Services Development Div.()
Date 1999/12/11
Paper # NC99-68
Volume (vol) vol.99
Number (no) 494
Page pp.pp.-
#Pages 8
Date of Issue