Pregled bibliografske jedinice broj: 1269775
Application of deep convolutional neural network for image scaling
Application of deep convolutional neural network for image scaling // Supplement of the Book of abstracts of the 16th International Symposium of Croatian Metallurgical Society - SHMD '2023, Materials and metallurgy (published in: Metalurgija 62 (2023) 3-4) / Mamuzić, Ilija (ur.).
Zagreb: Hrvatsko metalurško društvo, 2023. str. 494-494 (poster, međunarodna recenzija, sažetak, znanstveni)
CROSBI ID: 1269775 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Application of deep convolutional neural network for image scaling
Autori
Mamuzić, Ilija ; Dmitrieva, O. ; Misko, А. ; Huskova, V.
Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, znanstveni
Izvornik
Supplement of the Book of abstracts of the 16th International Symposium of Croatian Metallurgical Society - SHMD '2023, Materials and metallurgy (published in: Metalurgija 62 (2023) 3-4)
/ Mamuzić, Ilija - Zagreb : Hrvatsko metalurško društvo, 2023, 494-494
Skup
16th International Symposium of Croatian Metallurgical Society - SHMD '2023, Materials and metallurgy
Mjesto i datum
Zagreb, Hrvatska, 20.04.2023. - 21.04.2023
Vrsta sudjelovanja
Poster
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
neural network ; image scaling
Sažetak
This paper proposes a model of deep recursive neural network that takes into account the specific features of the input images, performs self-tuning with the definition of optimal scaling parameters and continues training. A unified deep learning neural network DJSR (Deep joint super resolution) was used to improve the quality of the output image. At the beginning the network is trained using an external image database, the tuning is done using the input image samples. The network can then be expanded into several specialized sub-networks, and sample learning is performed. The main idea is to exploit the surplus part-examples between different neighboring image scales. The proposed network contains a degradation model, a degradation discriminator, and a reconstruction model. The degradation model is used to produce realistic lowresolution images. The degradation discriminator ensures the similarity of the example parts of the obtained low-resolution image with the real images. The reconstruction model is used to directly create final high-resolution images by using the resulting images for training.
Izvorni jezik
Engleski
Znanstvena područja
Metalurgija
Napomena
The conference was canceled due the low number of presenters registered for the conference, but the Book of abstracts has been published.
