Abstract
Art styles have evolved over time in response to changing cultural, societal, and artistic influences. The naturalism and realism art styles emerged as artistic and philosophical movements in the 19th century, and while they had some similarities, they also had some important differences. There is, however, a challenge in fully recognizing and understanding the complexities of these art styles. This study aims to investigate how machine learning techniques, including LeNet, Pretrained ResNet-50, and Pretrained MobileNetV3 models, can be used to classify naturalism and realism art styles. The Pretrained MobileNetV3 model demonstrates superior performance for the classification of naturalism and realism, achieving an accuracy rate of 95% and outperforming other models in terms of Precision, Recall, F1-score, and overall accuracy. This model’s effectiveness in accurately classifying naturalism and realism art styles holds promise for various applications in art analysis, interpretation, and curation. This research contributes to advancing the understanding and application of machine learning in the field of art style classification. By utilizing suitable machine learning models, art researchers, historians, curators, and museum professionals will be able to analyze extensive art collections efficiently.
Author Information
Maftuhah Rahimah Rum, Asia University, Taiwan
Ardha Ardea Prisilla, LaSalle College Jakarta, Indonesia
Yori Pusparani, Budi Luhur University, Indonesia
Wen-Hung Chao, Asia University, Taiwan
Chi-Wen Lung, Asia University, Taiwan
Paper Information
Conference: KAMC2023
Stream: Digital Humanities
This paper is part of the KAMC2023 Conference Proceedings (View)
Full Paper
View / Download the full paper in a new tab/window
To cite this article:
Rum M., Prisilla A., Pusparani Y., Chao W., & Lung C. (2023) Using Machine Learning to Classify Art Style in Naturalism and Realism ISSN: 2436-0503 – The Kyoto Conference on Arts, Media & Culture 2023: Official Conference Proceedings https://doi.org/10.22492/issn.2436-0503.2023.34
To link to this article: https://doi.org/10.22492/issn.2436-0503.2023.34
Comments
Powered by WP LinkPress