LVQ of image sequence source and ANS classification of finite state machine for high compression coding

C. Manikopoulos, George Antoniou, S. Metzelopoulou

Research output: Contribution to conferencePaperResearchpeer-review

Abstract

Artificial neural system (ANS) classification has been applied to the total set of states of a finite-state machine operating as part of an image-sequence coder. It has been found that the classification of states allows the use of a much smaller number of representation states, thereby drastically reducing the storage requirements of the finite-state machine. The coder implements a scheme for high compression of teleconferencing image-sequence data. It utilizes neural-net-based learning vector quantization (LVQ) operating in the spatial domain on 16-dimensional vectors. The method is structured as a combination of an intraframe algorithm followed by an interframe algorithm, operating on a bundle of frames. The intraframe algorithm operates on the head frame of the bundle; the interframe algorithm follows in order to encode the remaining frames. Then, the encoding process repeats with a new bundle of frames. The intraframe and the interframe algorithms are finite state-based. Simulation experiments have been carried out for a videoconferencing image sequence consisting of 20 frames of 112 × 96 pixels, with 25% average block motion. The representation vectors were of 2 × 2 × 4 resolution. The results obtained have shown that for peak signal-to-noise ratio (PSNR) = 32 dB, the required bit rate is 0.08 to 0.10 b/pixel.

Original languageEnglish
Pages481-486
Number of pages6
StatePublished - 1 Dec 1990
Event1990 International Joint Conference on Neural Networks - IJCNN 90 - San Diego, CA, USA
Duration: 17 Jun 199021 Jun 1990

Other

Other1990 International Joint Conference on Neural Networks - IJCNN 90
CitySan Diego, CA, USA
Period17/06/9021/06/90

Fingerprint

Vector quantization
Finite automata
Head frames
Pixels
Teleconferencing
Signal to noise ratio
Neural networks
Experiments

Cite this

Manikopoulos, C., Antoniou, G., & Metzelopoulou, S. (1990). LVQ of image sequence source and ANS classification of finite state machine for high compression coding. 481-486. Paper presented at 1990 International Joint Conference on Neural Networks - IJCNN 90, San Diego, CA, USA, .
Manikopoulos, C. ; Antoniou, George ; Metzelopoulou, S. / LVQ of image sequence source and ANS classification of finite state machine for high compression coding. Paper presented at 1990 International Joint Conference on Neural Networks - IJCNN 90, San Diego, CA, USA, .6 p.
@conference{44beca1e53b54dd6b2cc436770a2d326,
title = "LVQ of image sequence source and ANS classification of finite state machine for high compression coding",
abstract = "Artificial neural system (ANS) classification has been applied to the total set of states of a finite-state machine operating as part of an image-sequence coder. It has been found that the classification of states allows the use of a much smaller number of representation states, thereby drastically reducing the storage requirements of the finite-state machine. The coder implements a scheme for high compression of teleconferencing image-sequence data. It utilizes neural-net-based learning vector quantization (LVQ) operating in the spatial domain on 16-dimensional vectors. The method is structured as a combination of an intraframe algorithm followed by an interframe algorithm, operating on a bundle of frames. The intraframe algorithm operates on the head frame of the bundle; the interframe algorithm follows in order to encode the remaining frames. Then, the encoding process repeats with a new bundle of frames. The intraframe and the interframe algorithms are finite state-based. Simulation experiments have been carried out for a videoconferencing image sequence consisting of 20 frames of 112 × 96 pixels, with 25{\%} average block motion. The representation vectors were of 2 × 2 × 4 resolution. The results obtained have shown that for peak signal-to-noise ratio (PSNR) = 32 dB, the required bit rate is 0.08 to 0.10 b/pixel.",
author = "C. Manikopoulos and George Antoniou and S. Metzelopoulou",
year = "1990",
month = "12",
day = "1",
language = "English",
pages = "481--486",
note = "null ; Conference date: 17-06-1990 Through 21-06-1990",

}

Manikopoulos, C, Antoniou, G & Metzelopoulou, S 1990, 'LVQ of image sequence source and ANS classification of finite state machine for high compression coding' Paper presented at 1990 International Joint Conference on Neural Networks - IJCNN 90, San Diego, CA, USA, 17/06/90 - 21/06/90, pp. 481-486.

LVQ of image sequence source and ANS classification of finite state machine for high compression coding. / Manikopoulos, C.; Antoniou, George; Metzelopoulou, S.

1990. 481-486 Paper presented at 1990 International Joint Conference on Neural Networks - IJCNN 90, San Diego, CA, USA, .

Research output: Contribution to conferencePaperResearchpeer-review

TY - CONF

T1 - LVQ of image sequence source and ANS classification of finite state machine for high compression coding

AU - Manikopoulos, C.

AU - Antoniou, George

AU - Metzelopoulou, S.

PY - 1990/12/1

Y1 - 1990/12/1

N2 - Artificial neural system (ANS) classification has been applied to the total set of states of a finite-state machine operating as part of an image-sequence coder. It has been found that the classification of states allows the use of a much smaller number of representation states, thereby drastically reducing the storage requirements of the finite-state machine. The coder implements a scheme for high compression of teleconferencing image-sequence data. It utilizes neural-net-based learning vector quantization (LVQ) operating in the spatial domain on 16-dimensional vectors. The method is structured as a combination of an intraframe algorithm followed by an interframe algorithm, operating on a bundle of frames. The intraframe algorithm operates on the head frame of the bundle; the interframe algorithm follows in order to encode the remaining frames. Then, the encoding process repeats with a new bundle of frames. The intraframe and the interframe algorithms are finite state-based. Simulation experiments have been carried out for a videoconferencing image sequence consisting of 20 frames of 112 × 96 pixels, with 25% average block motion. The representation vectors were of 2 × 2 × 4 resolution. The results obtained have shown that for peak signal-to-noise ratio (PSNR) = 32 dB, the required bit rate is 0.08 to 0.10 b/pixel.

AB - Artificial neural system (ANS) classification has been applied to the total set of states of a finite-state machine operating as part of an image-sequence coder. It has been found that the classification of states allows the use of a much smaller number of representation states, thereby drastically reducing the storage requirements of the finite-state machine. The coder implements a scheme for high compression of teleconferencing image-sequence data. It utilizes neural-net-based learning vector quantization (LVQ) operating in the spatial domain on 16-dimensional vectors. The method is structured as a combination of an intraframe algorithm followed by an interframe algorithm, operating on a bundle of frames. The intraframe algorithm operates on the head frame of the bundle; the interframe algorithm follows in order to encode the remaining frames. Then, the encoding process repeats with a new bundle of frames. The intraframe and the interframe algorithms are finite state-based. Simulation experiments have been carried out for a videoconferencing image sequence consisting of 20 frames of 112 × 96 pixels, with 25% average block motion. The representation vectors were of 2 × 2 × 4 resolution. The results obtained have shown that for peak signal-to-noise ratio (PSNR) = 32 dB, the required bit rate is 0.08 to 0.10 b/pixel.

UR - http://www.scopus.com/inward/record.url?scp=0025545469&partnerID=8YFLogxK

M3 - Paper

SP - 481

EP - 486

ER -

Manikopoulos C, Antoniou G, Metzelopoulou S. LVQ of image sequence source and ANS classification of finite state machine for high compression coding. 1990. Paper presented at 1990 International Joint Conference on Neural Networks - IJCNN 90, San Diego, CA, USA, .