Deep Learning-Based Layout Analysis Method for Complex Layout Image Elements
Source abstract
Abstract
The layout analysis of elements is indispensable in graphic design, as effective layout design not only facilitates the delivery of visual information but also enhances the overall esthetic appeal to the audience. The combination of deep learning and graphic design has gradually turned into a popular research direction in graphic design in recent years. However, in the era of rapid development of artificial intelligence, the analysis of layout still requires manual participation. To address this problem, this paper proposes a method for analyzing the layout of complex layout image elements based on the improved DeepLabv3++ model. The method reduces the number of model parameters and training time by replacing the backbone network. To improve the effect of multi-scale semantic feature extraction, the null rate of ASPP is fine-tuned, and the model is trained by self-constructed movie poster dataset. The experimental results show that the improved DeepLabv3+ model achieves a better segmentation effect on the self-constructed poster dataset, with MIoU reaching 75.60%. Compared with the classical models such as FCN, PSPNet, and DeepLabv3, the improved model in this paper effectively reduces the number of model parameters and training time while also ensuring the accuracy of the model.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Advanced Neural Network Applications · Image and Object Detection Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Packaging Engineering, Hunan University of Technology, Zhuzhou 412007, China
Funding
Natural Science Foundation of Hunan Province
References (31)
Show source-provided references
1. Visual communication design of digital media in digital advertising10.26689/jcer.v5i7.2312 ↗
2. Image aesthetic quality assessment: A survey
3. Image aesthetic assessment: An experimental survey10.1109/MSP.2017.2696576 ↗
4. She, D., Lai, Y.-K., Yi, G., and Xu, K. (2021, January 19–25). Hierarchical layout-aware graph convolutional network for unified aesthetics assessment. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR, Online.10.1109/CVPR46437.2021.00837 ↗
5. Analysis of Design Elements on Secret Magic Control Agency Movie Poster10.61405/tama.v1i1.684 ↗
6. Advances in deep learning-based image recognition of product packaging10.1016/j.imavis.2022.104571 ↗
7. George, N., and Sharad, C.S. (August, January 30). Hierarchical image representation with application to optically scanned documents. Proceedings of the 7th International Conference on Pattern Recognition (ICPR), Montreal, QC, Canada. Available online: http://digitalcommons.unl.edu/cseconfwork.
8. Document structure analysis algorithms: A literature survey
9. Ha, J., Haralick, R.M., and Phillips, I.T. (1995, January 14–18). Document page decomposition by the bounding-box project. Proceedings of the IEEE 3rd International Conference on Document Analysis and Recognition, Montreal, QC, Canada.
10. Pu, Y., Liu, D., Chen, S., and Zhong, Y. (2023). Research Progress on the Aesthetic Quality Assessment of Complex Layout Images Based on Deep Learning. Appl. Sci., 13.10.3390/app13179763 ↗
11. Document image layout analysis via explicit edge embedding network10.1016/j.ins.2021.07.020 ↗
12. Guo, S., Jin, Z., Sun, F., Li, J., Li, Z., Shi, Y., and Cao, N. (2021, January 8–13). Vinci: An intelligent graphic design system for generating advertising posters. Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, New Orleans, LA, USA.10.1145/3411764.3445117 ↗
13. A Study of Artificial Intelligence-Based Poster Layout Design in Visual Communication
14. Chen, L.C., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv.
15. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs10.1109/TPAMI.2017.2699184 ↗
16. Chollet, F. (2017, January 21–26). Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.195 ↗
17. Howard, A., Sandler, M., Chen, B., Wang, W., Chen, L.-C., Tan, M., Chu, G., Vasudevan, V., Zhu, Y., and Pang, R. (November, January 27). Searching for mobilenetv3. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
18. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A., and Liu, W. (2015, January 7–12). Going deeper with convolutions. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.10.1109/CVPR.2015.7298594 ↗
19. The pascal visual object classes challenge: A retrospective10.1007/s11263-014-0733-5 ↗
20. Long, J., Shelhamer, E., and Darrell, T. (2015, January 7–12). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298965 ↗
21. Zhao, H., Shi, J., Qi, X., Wang, X., and Jia, J. (2017, January 21–26). Pyramid scene parsing network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.660 ↗
22. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the MICCAI 2015, Munich, Germany. Available online: https://arxiv.org/abs/1505.04597.
23. Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., and Sang, N. (2018, January 8–14). BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation. Proceedings of the ECCV 2018, Munich, Germany. Available online: https://arxiv.org/abs/1808.00897.
24. Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., and Luo, P. (2021, January 6–14). SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers. Proceedings of the Advances in Neural Information Processing Systems, Online. Available online: https://arxiv.org/abs/2105.15203.
25. ImageNet classification with deep convolutional neural networks10.1145/3065386 ↗
26. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv.
27. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
28. Cabini, R.F., Tettamanti, H., and Zanella, M. (2025). Understanding the Impact of Evaluation Metrics in Kinetic Models for Consensus-Based Segmentation. Entropy, 27.10.3390/e27020149 ↗
29. A Kinetic Approach to Consensus-Based Segmentation of Biomedical Images10.3934/krm.2024017 ↗
30. Ye, M., Zhang, J., Liu, J., Liu, C., Yin, B., Liu, C., and Tao, D. (2024). Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation. arXiv.10.1109/TPAMI.2024.3495831 ↗
31. Ding, L., Liu, Y., Zhao, Q., and Liu, Y. (2024). Text Font Correction and Alignment Method for Scene Text Recognition. Sensors, 24.10.3390/s24247917 ↗