Abstract
Image complexity is an important indicator in computer vision that helps people to more accurately evaluate and understand visual image information. Compared with traditional regression algorithms, ordinal regression methods are better suited to handling relationships and structures among ordinal data, providing more accurate reference for image complexity assessment. Currently, IC9600 dataset has made significant progress for providing the largest image complexity dataset, and ICNet provided a baseline model to evaluate the complexity score of images, but it neglects the ordinal property of complexity scores. This paper focuses on exploring a method to evaluate image complexity based on deep ordinal regression. We propose an evaluation model (ICCORN) that combines convolutional neural network ICNet and ordinal regression approach CORN. The model firstly extracts global semantic information and local detail information, and then considers ordinal relationship between complexity scores in the prediction process. The model demonstrates a high degree of correlation with human perception, as indicated by an increased Pearson correlation coefficient of 0.955. Furthermore, other evaluation metrics have also yielded favorable results.
This work is partially supported by the Youth Program of the National Natural Science Foun-dation of China (61603228, 62006146), Natural Science Research Pro-gram of Shanxi Prov-ince Basic Research Program (202203021221029), Youth Project of Applied Basic Research Program of Shanxi Province (20210302123030), and Funds for central-government-guided local science and technology development (YDZJSX20231C001).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Nadal, M., Munar, E., Marty, G., Cela-Conde, C.J.: Visual complexity and beauty appreciation: explaining the divergence of results. Empir. Stud. Arts 28(2), 173–191 (2010)
Guo, X., Li, W., Qian, Y., Bai, R., Jia, C.: A review of computational methods for image complexity assessment. Acta Electron. Sin. 48(4), 819–826 (2020)
Niu, Z., Zhou, M., Wang, L., Gao, X.: Ordinal regression with multiple output CNN for age estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4920–4928 (2016). https://doi.org/10.1109/CVPR.2016.532
DÃaz, R., Marathe, A.: Soft labels for ordinal regression. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4733–4742 (2019)
Lee, Y.J., Efros, A.A., Hebert, M.: Style-aware mid-level representation for discovering visual connections in space and time. In: Proceedings of the 2013 IEEE International Conference on Computer Vision (ICCV), pp. 1857–1864 (2013)
Xiao, Y., Liu, B., Hao, Z.: Multiple-instance ordinal regression. IEEE Trans. Neural Netw. Learn. Syst. 29(9), 4398–4413 (2018)
Vargas, V.M., Gutierrez, P.A., Hervas-Martinez, C.: Cumulative link models for deep ordinal classification. Neurocomputing 401, 48–58 (2020)
Feng, T., et al.: IC9600: a benchmark dataset for automatic image complexity assessment. IEEE Trans. Pattern Anal. Mach. Intell. 45(7), 8577–8593 (2023)
Cardaci, M., Di Gesù, V., Petrou, M., Tabacchi, M.E.: A fuzzy approach to the evaluation of image complexity. Fuzzy Sets Syst. 160, 1474–1484 (2009)
Mayer, S., Landwehr, J.: When complexity is symmetric: the interplay of two core determinants of visual aesthetics. Adv. Cogn. Psychol. 10, 71–80 (2014)
Guo, X., Qian, Y., Li, L., Asano, A.: Assessment model for perceived visual complexity of painting images. Knowl.-Based Syst. 159, 110–119 (2018)
Nagle, F., Lavie, N.: Predicting human complexity perception of real-world scienes. R. Soc. Open Sci. 7(191487), 1–14 (2020). https://doi.org/10.1098/rsos.191487
Saraee, E., Jalal, M., Betke, M.: Visual complexity analysis using deep intermediate-layer features. Comput. Vis. Image Understand. 195, 1–13 (2020)
Kyle-Davidson, C., Zhou, E.Y., Walther, D.B., Bors, A.G., Evans, K.K.: Characterising and dissecting human perception of scene complexity. Cognition 231, 105319 (2023)
Kyle-Davidson, C., Bors, A.G., Evans, K.K.: Predicting human perception of scene complexity. In: IEEE International Conference on Image Processing (ICIP), pp. 1281–1285 (2022)
Chen, S., Zhang, C., Dong, M., Le, J., Rao, M.: Using ranking-CNN for age estimation. In: Computer Vision and Pattern Recognition (CVPR), pp. 5183–5192 (2017)
Cao, W., Mirjalili, V., Raschka S.: Consistent rank logits for ordinal regression with convolutional neural networks. arXiv preprint arXiv:1901.078846 (2019)
Shi, X., Cao, W.: Deep neural networks for rank-consistent ordinal regression based on conditional probabilities. arXiv preprintarXiv:2111.08851 (2021)
Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. Int. J. Comput. Vision 88, 303–338 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Guo, X., Wang, L., Yan, T., Wei, Y. (2024). Image Visual Complexity Evaluation Based on Deep Ordinal Regression. In: Liu, Q., et al. Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14435. Springer, Singapore. https://doi.org/10.1007/978-981-99-8552-4_16
Download citation
DOI: https://doi.org/10.1007/978-981-99-8552-4_16
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8551-7
Online ISBN: 978-981-99-8552-4
eBook Packages: Computer ScienceComputer Science (R0)