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

<p>With the continuous progress of image processing technology and deep neural networks, image style conversion has a wide range of applications in game production. This paper focuses on the application of silk screen printmaking technology in animation game production, using the DiracNet algorithm to express the features of image data, to realize the feature extraction of silk screen printmaking, and add attention mechanism and auxiliary classifier on the AnimeGANv2 model for improvement, to complete the style migration process of silk screen printmaking in animation game production, and to complete the silk screen printmaking technology’s pattern recognition and automatic rendering. Through the key point matching test of the model and the subjective and objective quantitative evaluation of the style migration of screen prints, the model is mined for its effect in pattern recognition and automatic rendering of screen prints technology. The model in this paper has better performance in feature extraction in multi-scenes, and the matching scores and mAP values are improved by 7.14%~25.82% and 11.51%~35.14% over the comparison algorithms, respectively. Most of the SSIM values of the sample screen print style migration images are greater than 0.3, and the overall aesthetic and migration effect evaluations are greater than 3.5. The model in this paper is capable of recognizing screen print patterns and auto-rendering effects, and it has a wide range of potential applications in the production of animation games.</p>
</abstract>

With the continuous progress of image processing technology and deep neural networks, image style conversion has a wide range of applications in game production. This paper focuses on the application of silk screen printmaking technology in animation game production, using the DiracNet algorithm to express the features of image data, to realize the feature extraction of silk screen printmaking, and add attention mechanism and auxiliary classifier on the AnimeGANv2 model for improvement, to complete the style migration process of silk screen printmaking in animation game production, and to complete the silk screen printmaking technology’s pattern recognition and automatic rendering. Through the key point matching test of the model and the subjective and objective quantitative evaluation of the style migration of screen prints, the model is mined for its effect in pattern recognition and automatic rendering of screen prints technology. The model in this paper has better performance in feature extraction in multi-scenes, and the matching scores and mAP values are improved by 7.14%~25.82% and 11.51%~35.14% over the comparison algorithms, respectively. Most of the SSIM values of the sample screen print style migration images are greater than 0.3, and the overall aesthetic and migration effect evaluations are greater than 3.5. The model in this paper is capable of recognizing screen print patterns and auto-rendering effects, and it has a wide range of potential applications in the production of animation games.

Pattern Recognition and Automatic Rendering of Silkscreen Printmaking Technology in Animation and Game Production

Applied Mathematics and Nonlinear Sciences

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

With the continuous progress of image processing technology and deep neural networks, image style conversion has a wide range of applications in game...

Pattern Recognition and Automatic Rendering of Silkscreen Printmaking Technology in Animation and Game Production

Pubblicato online: 05 lug 2024

Pagine: -

Ricevuto: 01 mar 2024

Accettato: 20 mag 2024

DOI: https://doi.org/10.2478/amns-2024-1683

Parole chiave
DiracNet, Feature extraction, Ani-meGANv2, Style migration, Screen prints, Game production

© 2024 Chuanyong Du., published by Sciendo

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

Pattern Recognition and Automatic Rendering of Silkscreen Printmaking Technology in Animation and Game Production

Pubblicato online: 05 lug 2024

Pagine: -

Ricevuto: 01 mar 2024

Accettato: 20 mag 2024

DOI: https://doi.org/10.2478/amns-2024-1683

Parole chiaveDiracNet, Feature extraction, Ani-meGANv2, Style migration, Screen prints, Game production

© 2024 Chuanyong Du., published by Sciendo

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

Parole chiave
DiracNet, Feature extraction, Ani-meGANv2, Style migration, Screen prints, Game production