Efficient Halftoning via Deep Reinforcement Learning

Halftoning aims to reproduce a continuous-tone image with pixels whose intensities are constrained to two discrete levels. This technique has been deployed on every printer, and the majority of them adopt fast methods (e.g., ordered dithering, error diffusion) that fail to render structural details,...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on image processing 2023, Vol.32, p.1-1
Hauptverfasser:	Jiang, Haitian, Xiong, Dongliang, Jiang, Xiaowen, Ding, Li, Chen, Liang, Huang, Kai
Format:	Artikel
Sprache:	eng
Schlagworte:	Anisotropy Artificial neural networks blue noise Convolutional neural networks Deep learning Diffusion rate dithering Extensibility Halftoning Machine learning Measurement Noise generation Optimization Pixels Reinforcement learning Training Visualization Weight reduction
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!