Movie generation based on higher-order features of music
-
- Kobori Takamasa
- School of Media Science, Tokyo University of Technology
-
- Obuchi Yasunari
- School of Media Science, Tokyo University of Technology
Bibliographic Information
- Other Title
-
- 音楽からの高次特徴抽出に基づく映像生成
Abstract
When posting their music on the Internet, professional musicians create their own videos or order videos, but this is not always easy for amateur composers due to financial and other reasons. In this research, we have developed a program that analyzes music and automatically creates videos. Using machine learning, we extracted abstract features of the music such as “brightness,” “orderliness,” and “organicity” as numerical values, and built a system that automatically creates images according to these values. The video was based on the frequency spectrum, volume, and audio waveform, and its lines and colors were changed according to those higher-order features to make the video more suitable for the music.
Journal
-
- Reports of the Technical Conference of the Institute of Image Electronics Engineers of Japan
-
Reports of the Technical Conference of the Institute of Image Electronics Engineers of Japan 21.04 (0), 290-291, 2022
The Institute of Image Electronics Engineers of Japan
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390577078293320704
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
-
- Abstract License Flag
- Disallowed