Geodesic
Noise reduction in digital images based on original RAW files using neural networks
Journal of computational and engineering mathematics, Tome 11 (2024) no. 4, pp. 64-74.

Voir la notice de l'article provenant de la source Math-Net.Ru

This paper presents a noise reduction method for RAW photo images, focusing on preserving the original information and improving the processing quality. Digital image processing is important for surveillance and vision systems where quality and detail play a key role. The proposed method is based on a combination of UNet and HQSNet neural networks. HQSNet performs semi-square partitioning of the input data, emphasizing key regions and reducing the dimensionality of less significant ones. UNet, in turn, efficiently processes the prepared data, preserving high granularity and tone transitions. The method is tested on real images, including complex night portrait and starry sky scenes, demonstrating high performance on MSE metrics and expert evaluations. Comparison with traditional methods, such as median and Bilateral filters, showed the superiority of the new approach in both noise removal quality and image detail preservation. The advantages of the method include preservation of dynamic range and the possibility of deep post-processing. The results obtained confirm its effectiveness in digital processing problems, which makes the development promising for application in automatic image analysis and enhancement systems.
Keywords: noise reduction, neural networks, UNet, HQSNet, RAW photo images. 
@article{JCEM_2024_11_4_a6,
     author = {A. A. Zamyshlyaeva and A. L. Kim},
     title = {Noise reduction in digital images based on original {RAW} files using neural networks},
     journal = {Journal of computational and engineering mathematics},
     pages = {64--74},
     publisher = {mathdoc},
     volume = {11},
     number = {4},
     year = {2024},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/JCEM_2024_11_4_a6/}
}
TY  - JOUR
AU  - A. A. Zamyshlyaeva
AU  - A. L. Kim
TI  - Noise reduction in digital images based on original RAW files using neural networks
JO  - Journal of computational and engineering mathematics
PY  - 2024
SP  - 64
EP  - 74
VL  - 11
IS  - 4
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/JCEM_2024_11_4_a6/
LA  - en
ID  - JCEM_2024_11_4_a6
ER  - 
%0 Journal Article
%A A. A. Zamyshlyaeva
%A A. L. Kim
%T Noise reduction in digital images based on original RAW files using neural networks
%J Journal of computational and engineering mathematics
%D 2024
%P 64-74
%V 11
%N 4
%I mathdoc
%U http://geodesic.mathdoc.fr/item/JCEM_2024_11_4_a6/
%G en
%F JCEM_2024_11_4_a6
A. A. Zamyshlyaeva; A. L. Kim. Noise reduction in digital images based on original RAW files using neural networks. Journal of computational and engineering mathematics, Tome 11 (2024) no. 4, pp. 64-74. http://geodesic.mathdoc.fr/item/JCEM_2024_11_4_a6/