Wavelet-Integrated Deep Networks for Single Image Super-Resolution

We propose a scale-invariant deep neural network model based on wavelets for single image super-resolution (SISR). The wavelet approximation images and their corresponding wavelet sub-bands across all predefined scale factors are combined to form a big training data set. Then, mappings are determine...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Electronics (Basel) 2019-05, Vol.8 (5), p.553
Hauptverfasser:	Sahito, Faisal, Zhiwen, Pan, Ahmed, Junaid, Memon, Raheel Ahmed
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Approximation Artificial neural networks Decomposition Deep learning Dictionaries Discrete Wavelet Transform HDTV High definition television Image resolution Mathematical analysis Neural networks Pattern recognition Principal components analysis Redundancy Signal to noise ratio Sparsity Training Wavelet transforms
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!