Überwachte Methoden für die spektrale Entmischung mit künstlichen neuronalen Netzen

• Autore principale: Anastasiadis, Johannes (auth)
• Natura: Elettronico Capitolo di libro
• Pubblicazione: KIT Scientific Publishing 2023
• Serie: Forschungsberichte aus der Industriellen Informationstechnik 29
• Soggetti: Electrical engineering; data generation; data augmentation; supervised training; artificial neural network; hyperspectral image; Datenerzeugung; Datenaugmentierung; überwachtes Training; Hyperspektralbild; künstliche neuronale Netze
• Accesso online: OAPEN Library: download the publication; OAPEN Library: description of the publication

Riassunto

In this work, artificial neural networks trained in a supervised manner for spectral unmixing are investigated. For this purpose, a suitable network architecture is determined first. After that, the focus lies on the generation of suitable training data. Model-based methods that generate training data from real pure spectra and data-based methods that augment existing training data are presented and evaluated.

Descrizione fisica

1 electronic resource (198 p.)

ISBN

KSP/1000159281

Accesso

Open Access