Data-Driven Convolutional Model for Digital Color Image Demosaicing

Modern digital cameras use specific arrangement of Color Filter Array to sample light wavelength corresponding to visible colors. The most common Color Filter Array is the Bayer filter that samples only one color per pixel. To recover the full resolution image, an interpolation algorithm can be used...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Francesco de Gioia, Luca Fanucci
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
T
Acceso en línea:https://doaj.org/article/cb29d4bd318b4e9195214d6ce096b0a4
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:cb29d4bd318b4e9195214d6ce096b0a4
record_format dspace
spelling oai:doaj.org-article:cb29d4bd318b4e9195214d6ce096b0a42021-11-11T15:03:30ZData-Driven Convolutional Model for Digital Color Image Demosaicing10.3390/app112199752076-3417https://doaj.org/article/cb29d4bd318b4e9195214d6ce096b0a42021-10-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/9975https://doaj.org/toc/2076-3417Modern digital cameras use specific arrangement of Color Filter Array to sample light wavelength corresponding to visible colors. The most common Color Filter Array is the Bayer filter that samples only one color per pixel. To recover the full resolution image, an interpolation algorithm can be used. This process is called demosaicing and it is one of the first processing stages of a digital imaging pipeline. We introduce a novel data-driven model for demosaicing that takes into account the different requirements for reconstruction of the image Luma and Chrominance channels. The final model is a parallel composition of two reconstruction networks with individual architecture and trained with distinct loss functions. In order to solve the overfitting problem, we prepared a dataset that contains groups of patches that share common chromatic and spectral characteristics. We reported the reconstruction error on noise-free images and measured the effect of random noise and quantization noise in the demosaicing reconstruction. To test our model performance, we implemented the network on NVIDIA Jetson Nano, obtaining an end-to-end running time of less than one second for a full frame 12 MPixel image.Francesco de GioiaLuca FanucciMDPI AGarticledemosaicingbayer filtercolor filter arrayconvolutional neural networkimage processingTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 9975, p 9975 (2021)
institution DOAJ
collection DOAJ
language EN
topic demosaicing
bayer filter
color filter array
convolutional neural network
image processing
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
spellingShingle demosaicing
bayer filter
color filter array
convolutional neural network
image processing
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
Francesco de Gioia
Luca Fanucci
Data-Driven Convolutional Model for Digital Color Image Demosaicing
description Modern digital cameras use specific arrangement of Color Filter Array to sample light wavelength corresponding to visible colors. The most common Color Filter Array is the Bayer filter that samples only one color per pixel. To recover the full resolution image, an interpolation algorithm can be used. This process is called demosaicing and it is one of the first processing stages of a digital imaging pipeline. We introduce a novel data-driven model for demosaicing that takes into account the different requirements for reconstruction of the image Luma and Chrominance channels. The final model is a parallel composition of two reconstruction networks with individual architecture and trained with distinct loss functions. In order to solve the overfitting problem, we prepared a dataset that contains groups of patches that share common chromatic and spectral characteristics. We reported the reconstruction error on noise-free images and measured the effect of random noise and quantization noise in the demosaicing reconstruction. To test our model performance, we implemented the network on NVIDIA Jetson Nano, obtaining an end-to-end running time of less than one second for a full frame 12 MPixel image.
format article
author Francesco de Gioia
Luca Fanucci
author_facet Francesco de Gioia
Luca Fanucci
author_sort Francesco de Gioia
title Data-Driven Convolutional Model for Digital Color Image Demosaicing
title_short Data-Driven Convolutional Model for Digital Color Image Demosaicing
title_full Data-Driven Convolutional Model for Digital Color Image Demosaicing
title_fullStr Data-Driven Convolutional Model for Digital Color Image Demosaicing
title_full_unstemmed Data-Driven Convolutional Model for Digital Color Image Demosaicing
title_sort data-driven convolutional model for digital color image demosaicing
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/cb29d4bd318b4e9195214d6ce096b0a4
work_keys_str_mv AT francescodegioia datadrivenconvolutionalmodelfordigitalcolorimagedemosaicing
AT lucafanucci datadrivenconvolutionalmodelfordigitalcolorimagedemosaicing
_version_ 1718437176885116928