Research on Digital Concept Art Illustrations Style Classification based on Deep Learning

DOI

10.2991/978-94-6463-370-2_40How to use a DOI?

Keywords

Deep Learning; Style Classification; Digital Concept Art

Abstract

With the development of the Internet, a large number of conceptual art pieces have been created in the form of digital images and uploaded to the internet, giving rise to a diverse range of digital image resources that cater to the needs of contemporary youth subcultures. Therefore, categorizing these digital resources by art style can help in the intelligent management of digital resource platforms. Additionally, it assists internet users who may have limited knowledge in art to understand and learn about various art styles. The deep convolutional neural network model represented by the ResNet network has achieved great success in image classification in the past. In recent years, the Vision Transformer model, which is improved based on the Transformer model that has performed brilliantly in the NLP field, has further improved the accuracy of image classification based on the self-attention mechanism.This article focuses on three commonly seen art styles on the Chinese internet and employs deep learning to examine the accuracy of three neural network models in handling binary and ternary classification problems related to these styles. The test and validation results obtained on the dataset were used to evaluate and compare the three models, and the model with better performance was selected to improve the accuracy of image style classification.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ziyang Li
PY  - 2024
DA  - 2024/02/14
TI  - Research on Digital Concept Art Illustrations Style Classification based on Deep Learning
BT  - Proceedings of the 2023 International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2023)
PB  - Atlantis Press
SP  - 379
EP  - 388
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-370-2_40
DO  - 10.2991/978-94-6463-370-2_40
ID  - Li2024
ER  -