A New Automatic Watercolour Painting Algorithm Based on Dual Stream Image Segmentation Model with Colour Space Estimation
Article Sidebar
Main Article Content
Abstract
Image processing plays a crucial role in automatic watercolor painting by manipulating the digital image to achieve the desired watercolor effect. segmentation in automatic watercolor painting algorithms is essential for region-based processing, color mixing and blending, capturing brushwork and texture, and providing artistic control over the final result. It allows for more realistic and expressive watercolor-like paintings by processing different image regions individually and applying appropriate effects to each segment. Hence, this paper proposed an effective Dual Stream Exception Maximization (DSEM) for automatic image segmentation. DSEM combines both color and texture information to segment an image into meaningful regions. This approach begins by converting the image from the RGB color space to a perceptually-based color space, such as CIELAB, to account for variations in lighting conditions and human perception of color. With the color space conversion, DSEM extracts relevant features from the image. Color features are computed based on the values of the color channels in the chosen color space, capturing the nuances of color distribution within the image. Simultaneously, texture features are derived by computing statistical measures such as local variance or co-occurrence matrices, capturing the textural characteristics of the image. Finally, the model is applied over the deep learning model for the classification of the color space in the painting. Simulation analysis is performed compared with conventional segmentation techniques such a CNN and RNN. The comparative analysis states that the proposed DSEM exhibits superior performance compared to conventional techniques in terms of color space estimation, texture analysis and region merging. The performance of classification with DSEM is ~12% higher than the conventional techniques.
Article Details
References
Zeng, X., Wu, Y., & Su, H. (2020). Watercolor image rendering based on color and texture blending. Signal Processing: Image Communication, 83, 115770.
Yang, L., Zhang, X., & Wu, Q. (2021). Watercolor style transfer using deep neural networks. Journal of Visual Communication and Image Representation, 77, 102945.
Yin, Y., Zheng, C., & Jiang, H. (2022). Watercolor painting generation with recurrent generative adversarial networks. Multimedia Tools and Applications, 81(15), 22233-22248.
Chang, J., & Kim, S. (2022). Watercolor-inspired stylization of images using generative adversarial networks. Journal of Visual Communication and Image Representation, 77, 102964.
Guo, J., Wang, W., & Zhang, X. (2022). Watercolor painting style transfer using unsupervised domain adaptation. ACM Transactions on Graphics, 41(4), 1-15.
Li, Y., Li, G., & Wang, Z. (2022). Automatic digital watercolor painting with enhanced brush stroke simulation. IEEE Transactions on Image Processing, 31, 5497-5510.
Yang, X., Chen, X., & Zhang, H. (2022). Watercolor painting style transfer with a unified framework. Neurocomputing, 492, 23-32.
Hwang, S., & Lee, D. (2022). Brushstroke analysis and synthesis for watercolor images. Computers & Graphics, 105, 1-11.
Park, S., Park, S., & Kim, S. (2022). WatercolorGAN: A generative adversarial network for watercolor painting synthesis. Computer Graphics Forum, 41(7), 157-166.
Li, S., Xia, K., & Wang, G. (2022). A deep learning framework for watercolor painting synthesis. Neurocomputing, 506, 427-436.
Chu, C., Tsai, Y., & Chen, H. (2022). Deep neural networks for automatic watercolor painting generation. Multimedia Tools and Applications, 81(19), 28829-28844.
Jin, L., & Wang, Z. (2023). WatercolorGAN++: An enhanced generative adversarial network for watercolor painting synthesis. Signal Processing: Image Communication, 112, 116354.
Huang, X., Zhang, Y., & Li, C. (2023). Automatic watercolor painting synthesis based on image content and user preferences. Journal of Visual Languages and Computing, 64, 100625.
Su, C., Liu, X., & Luo, Y. (2023). WatercolorGAN: A generative adversarial network for watercolor image synthesis. Multimedia Tools and Applications, 82(4), 5507-5523.
Wu, J., Liu, Z., & Yang, J. (2023). Learning a deep watercolor representation for style transfer. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (pp. 4212-4216).
J. Zhang and Z. Han. (2021). Watercolor Painting Style Transfer Using Neural Style Transfer and Texture Synthesis. In Proceedings of the 25th International Conference on Pattern Recognition (ICPR).
Y. Chen et al. (2021). Real-Time Watercolorization with Conditional Adversarial Networks. ACM Transactions on Graphics (TOG), 40(4).
Prof. Muhamad Angriawan. (2016). Performance Analysis and Resource Allocation in MIMO-OFDM Systems. International Journal of New Practices in Management and Engineering, 5(02), 01 - 07. Retrieved from http://ijnpme.org/index.php/IJNPME/article/view/44
Verma, R. ., & Sharma, N. . (2023). Impact of Inclusion of Information and Communication Technologies in School Facilities and Effective Learning of Students in Green School. International Journal of Intelligent Systems and Applications in Engineering, 11(2s), 27–34. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/2503
W. Liu et al. (2021). WatercolorGAN: A Deep Learning Approach for Watercolor Style Transfer. In Proceedings of the IEEE International Conference on Computer Vision (ICCV).
S. Xie et al. (2021). Brushstroke Style Transfer for Watercolor Paintings. In Proceedings of the 16th European Conference on Computer Vision (ECCV).
X. Zhang et al. (2022). Watercolorization of Line Art via Multi-Scale Adversarial Networks. IEEE Transactions on Multimedia, 24(3).
Kamau, J., Ben-David, Y., Santos, M., Joo-young, L., & Tanaka, A. Predictive Analytics for Customer Churn in the Telecom Industry. Kuwait Journal of Machine Learning, 1(3). Retrieved from http://kuwaitjournals.com/index.php/kjml/article/view/130
L. Li et al. (2022). Neural Watercolor: Stochastic Diffusion Network for Watercolor Painting Synthesis. In Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI).
Verma, D. ., Reddy, A. ., & Thota, D. S. . (2021). Fungal and Bacteria Disease Detection Using Feature Extraction with Classification Based on Deep Learning Architectures. Research Journal of Computer Systems and Engineering, 2(2), 27:32. Retrieved from https://technicaljournals.org/RJCSE/index.php/journal/article/view/29
Y. Zhang et al. (2022). Watercolor Painting Style Transfer Using Temporal Consistency. In Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
Y. Zhu et al. (2022). End-to-End Learning of Watercolor Style Transfer with Continuous Brushstroke Attention. In Proceedings of the 28th ACM International Conference on Multimedia (MM).
Z. Wu et al. (2023). WatercolorGAN++: Enhanced Watercolor Style Transfer with Progressive Growing and Attention Mechanism. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI).
H. Li et al. (2023). Watercolor-Net: A Deep Learning Framework for Watercolor Painting Synthesis. IEEE Transactions on Image Processing, 32.
Y. Wang et al. (2023). StrokeGAN: Stroke-Based Watercolor Style Transfer with Generative Adversarial Networks. In Proceedings of the 37th International Conference on Machine Learning (ICML).
X. Li et al. (2023). WatercolorGANv2: Enhancing Watercolor Style Transfer with Advanced Generator Architecture. In Proceedings of the 26th International Conference on Neural Information Processing (ICONIP).
M. Liu et al. (2023). Learning Watercolor Painting Styles from Artist Demonstrations using Siamese Networks. In Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI).
L. Zhang et al. (2023). Semi-Supervised Watercolor Painting Style Transfer with Consistency Learning. In Proceedings of the IEEE International Conference on Multimedia and Expo (ICME).