A Deep Learning based Artistic Generative Adversarial Networks (AGAN): A Weighted Architecture for Assessing Aesthetic Appeal
Keywords:
Art, Painting, Deep Learning, artistic techniques, deep generative adversarial networks (GANs), Dimensionality ReductionAbstract
The world of art has always been a captivating domain, with painting being one of the oldest and most cherished art forms. As technology continues to advance, there is a growing interest in exploring the intersection of art and deep learning to unlock new dimensions and possibilities. This paper aims to investigate the artistic value and future development of painting through the lens of deep learning. this study explores the potential applications of deep learning in assessing the artistic value of paintings. Through training deep neural networks on large datasets of renowned artworks, this paper developed models capable of analyzing visual elements, composition, and artistic techniques. The models enable us to quantify and compare the artistic merits of paintings, providing insights into the factors that contribute to their aesthetic appeal. Generative models, such as deep generative adversarial networks (GANs), generate novel and visually compelling artworks, pushing the boundaries of artistic creativity. The proposed Artistic Generative Adversarial Network (AGAN) comprises the Weighted architectural model for the formulation of the dataset to perform classification. The AGAN model performs dimensionality reduction for minimizing the complexity of the process. The experiment stated that the AGAN model achieves an overall accuracy of 98% with an error value of 0.001.
Downloads
References
Smith, A. B., & Johnson, C. D. (2021). Exploring the Impact of Artificial Intelligence on Healthcare Delivery. Journal of Medical Informatics, 45(3), 187-200.
Chen, X., Zhang, Y., & Wang, J. (2021). Deep Reinforcement Learning for Autonomous Vehicle Control in Urban Environments. IEEE Transactions on Intelligent Transportation Systems, 22(4), 2038-2051.
Lee, S., Kim, H., & Park, J. (2021). Blockchain Technology for Supply Chain Management: A Review and Future Directions. International Journal of Production Economics, 240, 107904.
Nguyen, T., Nguyen, H., & Nguyen, D. (2022). Deep Learning-Based Sentiment Analysis: A Comprehensive Review. Information Processing & Management, 59(2), 102646.
Patel, R., Chandra, S., & Gupta, R. (2022). Internet of Things (IoT) in Agriculture: Applications, Challenges, and Future Directions. Computers and Electronics in Agriculture, 191, 106257.
Li, M., Li, Z., & Wang, Y. (2022). Machine Learning Approaches for Credit Risk Assessment: A Review. Expert Systems with Applications, 190, 116791.
Kim, S., Lee, J., & Park, K. (2022). Augmented Reality in Education: A Review of Current Trends and Future Perspectives. Computers & Education, 181, 104679.
Singh, A., Dixit, A., & Mishra, S. (2023). Deep Learning-Based Image Forgery Detection: A Comprehensive Survey. Journal of Visual Communication and Image Representation, 82, 102046.
Yang, L., Zhang, Y., & Chen, H. (2023). Natural Language Processing for Social Media Analytics: A Review. Information Processing & Management, 60(1), 102651.
Wu, X., Jiang, Z., & Li, Y. (2023). Blockchain Technology for Secure and Efficient Healthcare Data Sharing: A Review. Journal of Biomedical Informatics, 124, 103821.
Huang, Q., Liu, X., & Zhang, H. (2023). Deep Learning Approaches for Traffic Flow Prediction: A Comprehensive Review. Transportation Research Part C: Emerging Technologies, 130, 103343.
Kim, Y., Park, S., & Lee, J. (2023). Deep Learning-Based Natural Language Generation: A Survey. Information Sciences, 628, 67-81.
Zhang, Y., et al. (2022). Aesthetic Quality Assessment of Images Using a Dual Attention Enhanced Convolutional Neural Network. IEEE Transactions on Image Processing, 31, 3987-4001.
Chen, H., et al. (2022). A Deep Learning Approach for Aesthetic Image Analysis: A Review. Journal of Visual Communication and Image Representation, 83, 102060.
Liu, W., et al. (2022). Deep Learning for Aesthetic Image Style Transfer. IEEE Transactions on Multimedia, 24, 2988-3001.
Wu, S., et al. (2023). Deep Learning for Aesthetic Assessment: A Survey. ACM Computing Surveys, 56(1), Article 11.
Li, Z., et al. (2022). Deep Aesthetic Quality Assessment of Art Images. IEEE Transactions on Multimedia, 24, 3669-3682.
Wang, L., et al. (2022). Aesthetic Assessment of Paintings Using Deep Learning. Pattern Recognition Letters, 162, 117-124.
Zhang, Y., et al. (2022). Deep Style Analysis for Aesthetic Image Evaluation. Neurocomputing, 474, 471-480.
Chen, H., et al. (2022). Aesthetic Object Detection Using Deep Learning. Pattern Recognition Letters, 160, 58-65.
Liu, W., et al. (2022). Deep Learning for Aesthetic Fashion Analysis. Pattern Recognition Letters, 158, 30-37.
Jiang, Y., et al. (2022). Learning Aesthetic Attributes for Image Aesthetics Assessment. Pattern Recognition, 124, 108187.
Wu, S., et al. (2022). Aesthetic Quality Assessment of User-Generated Videos Using Deep Learning. ACM Transactions on Multimedia Computing, Communications, and Applications, 18(4), Article 59.
Zhang, Y., et al. (2022). Generative Adversarial Networks for Aesthetic Image Enhancement. Neurocomputing, 490, 235-244.
Li, Z., et al. (2023). Deep Learning for Aesthetic Enhancement of Low-Quality Images. Information Sciences, 597, 200-213.
Chen, H., et al. (2023). Aesthetic Image Captioning Using Deep Learning. Neurocomputing, 505, 112-122.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
