<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>In this paper, using the loss function of image stylization, combined with the development of image stylization based on deep learning, the proposed convolutional neural network in the style of image conversion fitting and overfitting response. Based on this, the multi-scale feature fusion method is chosen to train the style conversion network, with the help of deep feature extraction of the image for style conversion, reconstruct the multi-scale feature fusion image, and send it to the decoder for deep coding to realize the style conversion. To evaluate the effectiveness of the proposed multi-scale feature fusion style conversion algorithm, the content loss and style loss parameters of the algorithm are analyzed using the lightweight encoder and VGG encoder, respectively. Calculate the number of algorithmic model parameters and the amount of computation. Analyze the change in the iteration number of the personalized art style conversion process and select the performance evaluation index to evaluate the results of the personalized art style image conversion process. In the process of personalized art style conversion, the multi-scale feature fusion algorithm network proposed in this paper can basically reconstruct the original image after 1000 iterations. Personalized style image reconstruction has a PSNR of 25.26 dB when the number of iterations is 1000. With the deepening of training, the reconstruction effect becomes better and better, and the advantages of personalized art style image conversion applications are significant.</p>
</abstract>

In this paper, using the loss function of image stylization, combined with the development of image stylization based on deep learning, the proposed convolutional neural network in the style of image conversion fitting and overfitting response. Based on this, the multi-scale feature fusion method is chosen to train the style conversion network, with the help of deep feature extraction of the image for style conversion, reconstruct the multi-scale feature fusion image, and send it to the decoder for deep coding to realize the style conversion. To evaluate the effectiveness of the proposed multi-scale feature fusion style conversion algorithm, the content loss and style loss parameters of the algorithm are analyzed using the lightweight encoder and VGG encoder, respectively. Calculate the number of algorithmic model parameters and the amount of computation. Analyze the change in the iteration number of the personalized art style conversion process and select the performance evaluation index to evaluate the results of the personalized art style image conversion process. In the process of personalized art style conversion, the multi-scale feature fusion algorithm network proposed in this paper can basically reconstruct the original image after 1000 iterations. Personalized style image reconstruction has a PSNR of 25.26 dB when the number of iterations is 1000. With the deepening of training, the reconstruction effect becomes better and better, and the advantages of personalized art style image conversion applications are significant.

A study on the application of neural style transformation technique in personalized art creation

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

In this paper, using the loss function of image stylization, combined with the development of image stylization based on deep learning, the proposed...

A study on the application of neural style transformation technique in personalized art creation

Pubblicato online: 05 ago 2024

Pagine: -

Ricevuto: 22 apr 2024

Accettato: 10 lug 2024

DOI: https://doi.org/10.2478/amns-2024-2241

Parole chiave
Multi-scale features, Feature extraction, Convolutional neural network, Image style transformation

© 2024 Yongtao Zhao, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

A study on the application of neural style transformation technique in personalized art creation

Pubblicato online: 05 ago 2024

Pagine: -

Ricevuto: 22 apr 2024

Accettato: 10 lug 2024

DOI: https://doi.org/10.2478/amns-2024-2241

Parole chiaveMulti-scale features, Feature extraction, Convolutional neural network, Image style transformation

© 2024 Yongtao Zhao, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Parole chiave
Multi-scale features, Feature extraction, Convolutional neural network, Image style transformation