Controlled feature adjustment for image processing and synthesis
| Autor: | Javier Portilla, Eduardo Martinez-Enriquez |
|---|---|
| Přispěvatelé: | Ministerio de Economía y Competitividad (España) |
| Rok vydání: | 2020 |
| Předmět: |
Signal processing
Computer science business.industry 010102 general mathematics Perspective (graphical) Process (computing) Meta-synthesis Image processing Pattern recognition No-reference synthesis 010501 environmental sciences 01 natural sciences Term (time) Set (abstract data type) Decoupled features Controlled feature adjustment Feature (computer vision) Nested normalizations Artificial intelligence 0101 mathematics business 0105 earth and related environmental sciences Parametric statistics |
| Zdroj: | Digital.CSIC. Repositorio Institucional del CSIC instname MMSP |
| Popis: | 6 pags., 8 figs., 1 tab. -- 2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP), Tampere, Finland, 21-24 Sept. 2020 Feature adjustment, understood as the process aimed at modifying at will global features of given signals, has cardinal importance for several signal processing applications, such as enhancement, restoration, style transfer, and synthesis. Despite of this, it has not yet been approached from a general, theory-grounded, perspective. This work proposes a new conceptual and practical methodology that we term Controlled Feature Adjustment (CFA). CFA provides methods for, given a set of parametric global features (scalar functions of discrete signals), (1) constructing a related set of deterministically decoupled features, and (2) adjusting these new features in a controlled way, i.e., each one independently of the others. We illustrate the application of CFA by devising a spectrally-based hierarchically decoupled feature set and applying it to obtain different types of image synthesis that are not achievable using traditional (coupled) feature sets. Funded by the Spanish Government grant FIS2016-75891-P |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|