The Retinex algorithms find wide applications as image enhancers, for their capability of preserving edges, while at the same time attenuating smooth gradients and chromatic dominants. They are characterized by the fact that the output chromatic intensity of a pixel is not determined in isolation (or looking only at the contiguous pixels) but through an operation of comparison to different local and remote areas of the image. This local/global comparison implies also a high computational cost for the algorithms: their complexity is not linear with the number of pixels; furthermore, the more systematic the comparison, the higher the complexity. Thus, most Retinex algorithms are unfit for real-time processing. The recent development of efficient Machine Learning architectures for Image Processing has raised the question of whether one of the Retinex "transforms" could be efficiently learned by training a feed-forward Artificial Neural Network, thus creating a model characterized by short processing time. Selecting a variant of the Random Spray Retinex model – FuzzyRSR – as representative of the Retinex family, and choosing suitably structured autoencoder neural networks, we found that we could accurately reproduce the Retinex effects. The computational cost of the training phase was moderate, while that of the inference phases was linear in the number of pixels, and three orders of magnitude lower than the one of FuzzyRSR, thus making the ANN implementation of Retinex suitable for real-time processing.
Retinex by Autoencoders / C. Pezzoni, C. Mio, A. Barsotti, G. Gianini - In: 2022 16th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)[s.l] : IEEE, 2023. - ISBN 978-1-6654-6495-6. - pp. 140-147 (( Intervento presentato al 16. convegno International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) tenutosi a Dijon nel 2022 [10.1109/SITIS57111.2022.00036].
Retinex by Autoencoders
C. MioSecondo
;A. BarsottiPenultimo
;G. Gianini
Ultimo
2023
Abstract
The Retinex algorithms find wide applications as image enhancers, for their capability of preserving edges, while at the same time attenuating smooth gradients and chromatic dominants. They are characterized by the fact that the output chromatic intensity of a pixel is not determined in isolation (or looking only at the contiguous pixels) but through an operation of comparison to different local and remote areas of the image. This local/global comparison implies also a high computational cost for the algorithms: their complexity is not linear with the number of pixels; furthermore, the more systematic the comparison, the higher the complexity. Thus, most Retinex algorithms are unfit for real-time processing. The recent development of efficient Machine Learning architectures for Image Processing has raised the question of whether one of the Retinex "transforms" could be efficiently learned by training a feed-forward Artificial Neural Network, thus creating a model characterized by short processing time. Selecting a variant of the Random Spray Retinex model – FuzzyRSR – as representative of the Retinex family, and choosing suitably structured autoencoder neural networks, we found that we could accurately reproduce the Retinex effects. The computational cost of the training phase was moderate, while that of the inference phases was linear in the number of pixels, and three orders of magnitude lower than the one of FuzzyRSR, thus making the ANN implementation of Retinex suitable for real-time processing.File | Dimensione | Formato | |
---|---|---|---|
bare_conf - one_column.pdf
accesso riservato
Tipologia:
Pre-print (manoscritto inviato all'editore)
Dimensione
3.71 MB
Formato
Adobe PDF
|
3.71 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Retinex_by_Autoencoders.pdf
accesso riservato
Tipologia:
Publisher's version/PDF
Dimensione
1.74 MB
Formato
Adobe PDF
|
1.74 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.