Digital movies using optimized feature maps

Yasuo Matsuyama*, Masayoshi Tan

*Corresponding author for this work

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


Steps from DC (data compression) to AC (animation coding) are discussed. This means that a digital movie is generated from a single still image using data compression. Such processing is made possible by the multiply optimized competitive learning (multiply descent cost competitive learning). A key point is the usage of the optimized feature map. This optimized feature map groups nearby pixels together. Therefore, it is also called grouping feature map. Since this grouping feature map is optimized with respect to the source image and standard weight vectors, it possesses the ability of source data recovery. This property can not be realized by plain feature maps. The grouping feature map and standard weight vectors are metamorphic. Given information to move vertices in the grouping feature map, modified images can be produced. Thus, by generating temporal key frames, digital movies are realized. An initial trial toward 3D image processing is also given.

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
Place of PublicationPiscataway, NJ, United States
Number of pages6
Publication statusPublished - 1994
Externally publishedYes
EventProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA
Duration: 1994 Jun 271994 Jun 29


OtherProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)
CityOrlando, FL, USA

ASJC Scopus subject areas

  • Software


Dive into the research topics of 'Digital movies using optimized feature maps'. Together they form a unique fingerprint.

Cite this