NONLINEAR PREDICTION IN IMAGE-CODING WITH DPCM

被引：7
作者：
LI, J
MANIKOPOULOS, CN
机构：
[1] Department of Electrical and Computer Engineering, New Jersey Institute of Technology, 07102 New Jersey, 323 King Blvd., Newark
来源：
ELECTRONICS LETTERS | 1990年 / 26卷 / 17期
关键词：
Image processing; Neural networks; Nonlinear networks;
D O I：
10.1049/el:19900873
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
In contrast to the traditional linear differential pulse code modulation (DPCM) design for the encoding of images, a new, nonlinear, neural network-based, DPCM technique has been devised. The predictor is designed by supervised train ing, based on a typical sequence of pixel values in an image. A function link neural network architecture has been used to design the predictor for one dimensional (1-D) DPCM. Com puter simulation experiments in still image coding have shown that the resulting encoders work very well. At a trans mission rate of 1 bit/pixel, for the image LENA, the 1-D neural network DPCM provides a 4-2 dB improvement in SNR over the standard linear DPCM system. © 1990, The Institution of Electrical Engineers. All rights reserved.
引用
收藏
页码：1357 / 1359
页数：3
相关论文
共 50 条
[11]   IMAGE-CODING AND DECODING BY DISCRETE-TIME CELLULAR NEURAL NETWORKS [J].
IKEGAMI, M ;
TANAKA, M .
ELECTRONICS AND COMMUNICATIONS IN JAPAN PART III-FUNDAMENTAL ELECTRONIC SCIENCE, 1995, 78 (03) :32-43
[12]   MAXIMUM-ENTROPY INITIALIZATION TECHNIQUE FOR IMAGE-CODING VECTOR QUANTIZER DESIGN [J].
NYECK, A ;
TOSSERROUSSEY, A .
ELECTRONICS LETTERS, 1992, 28 (03) :273-274
[13]   GENERALIZATION OF DPCM FOR DIGITAL IMAGE COMPRESSION [J].
HUNG, SHY .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1979, 1 (01) :100-109
[14]   DPCM coding of images presented in a pruned quadtree form [J].
Vergopoulos, SA ;
Sangriotis, MS ;
MetaxakiKossionides, C .
ELECTRONICS LETTERS, 1996, 32 (06) :531-533
[15]   NOISY FORCED ZERO PADDED DPCM PREDICTION [J].
QUINN, D ;
LACY, J .
ELECTRONICS LETTERS, 1992, 28 (13) :1223-1224
[16]   Speech coding through adaptive combined nonlinear prediction [J].
Faundez-Zanuy, Marcos .
SPEECH COMMUNICATION, 2006, 48 (07) :838-847
[17]   Use of nonlinear principal component analysis and vector quantization for image coding [J].
Tzovaras, D ;
Strintzis, MG .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 1998, 7 (08) :1218-1223
[18]   System-level design for DPCM Image Compression with SoC-FPGA Accelerator [J].
Safaei, Amin ;
Sabeti, Samira ;
Masoudian, Morteza .
2024 IEEE CANADIAN CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING, CCECE 2024, 2024, :887-891
[19]   The fractal method of the image coding [J].
Melnikov, Grigory N. .
SIBCON-2007: IEEE International Siberian Conference on Control and Communication, 2007, :153-157
[20]   Wavelet Coding of Image Using Quadtree and Vector Entropy Coding [J].
郑文星 .
HighTechnologyLetters, 1997, (01) :63-66
12345