Multiply descent cost competitive learning as an aid for multimedia image processing

Yasuo Matsuyama, Masayoshi Tan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

An integration of neural and ordinary computations toward multimedia processing is presented. The handled media is a combination of still images and animations. The neurocomputation here is the multiply descent cost competitive learning. This algorithm generates two types of feature maps. One of them, an optimized grouping pattern of pixels by self-organization, is used. A data-compressed still image can be recovered from this feature map by virtue of the multiply descent cost competitive learning. Next, this map is contorted according to a user's request. At the final step, a movie is virtually generated from the compressed still image via a set of animation tools. Thus, neurocomputation can be a useful item in the toolbox for creating the virtual reality besides the real-world computing.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Place of PublicationPiscataway, NJ, United States
PublisherPubl by IEEE
Pages2061-2064
Number of pages4
Volume3
ISBN (Print)0780314212, 9780780314214
Publication statusPublished - 1993
Externally publishedYes
EventProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) - Nagoya, Jpn
Duration: 1993 Oct 251993 Oct 29

Other

OtherProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3)
CityNagoya, Jpn
Period93/10/2593/10/29

Fingerprint

Image processing
Animation
Costs
Virtual reality
Pixels
Processing

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Matsuyama, Y., & Tan, M. (1993). Multiply descent cost competitive learning as an aid for multimedia image processing. In Proceedings of the International Joint Conference on Neural Networks (Vol. 3, pp. 2061-2064). Piscataway, NJ, United States: Publ by IEEE.

Multiply descent cost competitive learning as an aid for multimedia image processing. / Matsuyama, Yasuo; Tan, Masayoshi.

Proceedings of the International Joint Conference on Neural Networks. Vol. 3 Piscataway, NJ, United States : Publ by IEEE, 1993. p. 2061-2064.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Matsuyama, Y & Tan, M 1993, Multiply descent cost competitive learning as an aid for multimedia image processing. in Proceedings of the International Joint Conference on Neural Networks. vol. 3, Publ by IEEE, Piscataway, NJ, United States, pp. 2061-2064, Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3), Nagoya, Jpn, 93/10/25.
Matsuyama Y, Tan M. Multiply descent cost competitive learning as an aid for multimedia image processing. In Proceedings of the International Joint Conference on Neural Networks. Vol. 3. Piscataway, NJ, United States: Publ by IEEE. 1993. p. 2061-2064
Matsuyama, Yasuo ; Tan, Masayoshi. / Multiply descent cost competitive learning as an aid for multimedia image processing. Proceedings of the International Joint Conference on Neural Networks. Vol. 3 Piscataway, NJ, United States : Publ by IEEE, 1993. pp. 2061-2064
@inproceedings{bf123c909dd04706831f93e8d1519b6c,
title = "Multiply descent cost competitive learning as an aid for multimedia image processing",
abstract = "An integration of neural and ordinary computations toward multimedia processing is presented. The handled media is a combination of still images and animations. The neurocomputation here is the multiply descent cost competitive learning. This algorithm generates two types of feature maps. One of them, an optimized grouping pattern of pixels by self-organization, is used. A data-compressed still image can be recovered from this feature map by virtue of the multiply descent cost competitive learning. Next, this map is contorted according to a user's request. At the final step, a movie is virtually generated from the compressed still image via a set of animation tools. Thus, neurocomputation can be a useful item in the toolbox for creating the virtual reality besides the real-world computing.",
author = "Yasuo Matsuyama and Masayoshi Tan",
year = "1993",
language = "English",
isbn = "0780314212",
volume = "3",
pages = "2061--2064",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Multiply descent cost competitive learning as an aid for multimedia image processing

AU - Matsuyama, Yasuo

AU - Tan, Masayoshi

PY - 1993

Y1 - 1993

N2 - An integration of neural and ordinary computations toward multimedia processing is presented. The handled media is a combination of still images and animations. The neurocomputation here is the multiply descent cost competitive learning. This algorithm generates two types of feature maps. One of them, an optimized grouping pattern of pixels by self-organization, is used. A data-compressed still image can be recovered from this feature map by virtue of the multiply descent cost competitive learning. Next, this map is contorted according to a user's request. At the final step, a movie is virtually generated from the compressed still image via a set of animation tools. Thus, neurocomputation can be a useful item in the toolbox for creating the virtual reality besides the real-world computing.

AB - An integration of neural and ordinary computations toward multimedia processing is presented. The handled media is a combination of still images and animations. The neurocomputation here is the multiply descent cost competitive learning. This algorithm generates two types of feature maps. One of them, an optimized grouping pattern of pixels by self-organization, is used. A data-compressed still image can be recovered from this feature map by virtue of the multiply descent cost competitive learning. Next, this map is contorted according to a user's request. At the final step, a movie is virtually generated from the compressed still image via a set of animation tools. Thus, neurocomputation can be a useful item in the toolbox for creating the virtual reality besides the real-world computing.

UR - http://www.scopus.com/inward/record.url?scp=0027810273&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027810273&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0780314212

SN - 9780780314214

VL - 3

SP - 2061

EP - 2064

BT - Proceedings of the International Joint Conference on Neural Networks

PB - Publ by IEEE

CY - Piscataway, NJ, United States

ER -