Test time augmentation by regular shifting for deep denoising autoencoder networks

Image restoration, which is the process of denoising noisy images in order to recover their latent clean images, has been frequently addressed. The importance of this field resides in the impact of noisy images on the performance of computer vision systems. In this work, a deep autoencoder neural ne...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of ... International Joint Conference on Neural Networks s. 1 - 7
Hlavní autoři: Rodriguez-Rodriguez, Jose A., Molina-Cabello, Miguel A., Benitez-Rochel, Rafaela, Lopez-Rubio, Ezequiel
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 18.07.2021
Témata:
autoencoder
convolutional neural networks
Gaussian noise
image classification
Image restoration
Neural networks
Noise measurement
Noise reduction
Statistical analysis
Storage tanks
test time augmentation
ISSN:2161-4407
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Image restoration, which is the process of denoising noisy images in order to recover their latent clean images, has been frequently addressed. The importance of this field resides in the impact of noisy images on the performance of computer vision systems. In this work, a deep autoencoder neural network architecture is proposed to denoise images affected by Gaussian noise. The performance of the system is enhanced by using a test time augmentation scheme. Experiments have been carried out by considering different levels of Gaussian noise. Results demonstrate the suitability of the proposed methodology in order to enhance the quality of the image restoration process in images affected by Gaussian noise.
ISSN:2161-4407
DOI:10.1109/IJCNN52387.2021.9534044