Abstract
Art images can usually convey the background of the times, culture and the personal emotions of the painter. Appreciating visual art can not only close the distance with the artist, but also enrich our life. It becomes very meaningful to recognition the visual style through computer-aided means. However, the existing methods have not fully explored the correlation between regional styles, and it is difficult to fully describe the style information of artistic images. In this paper, we propose a two-branch network structure, which can aggregate graph style features and global style features. Specially, a graph network is introduced to construct the correlation between the styles of artistic image regions to capture graph style. In addition, we design a perceptual layer to learn cross-layer correlation features to capture global style. The experimental results demonstrate the superiority of the proposed method in three style datasets.
This work was supported by the National Natural Science Foundation of China under Grants 62072295 and Natural Science Foundation of Shanghai under Grant 19ZR1419000.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Bianco, S., Mazzini, D., Napoletano, P., Schettini, R.: Multitask painting categorization by deep multibranch neural network. Expert Syst. Appl. 135, 90–101 (2019)
Chu, W., Wu, Y.: Deep correlation features for image style classification. In: ACMMM, pp. 402–406 (2016)
Chu, W., Wu, Y.: Image style classification based on learnt deep correlation features. IEEE Trans. Multimed. 20(9), 2491–2502 (2018)
Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: CVPR, pp. 2414–2423 (2016)
Jia, Z., et al.: Graphsleepnet: adaptive spatial-temporal graph convolutional networks for sleep stage classification. In: IJCAI, pp. 1324–1330 (2020)
Karayev, S., et al.: Recognizing image style. In: BMVC, pp. 1–11 (2014)
Khan, F.S., Beigpour, S., van de Weijer, J., Felsberg, M.: Painting-91: a large scale database for computational painting categorization. Mach. Vis. Appl. 25(6), 1385–1397 (2014). https://doi.org/10.1007/s00138-014-0621-6
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1106–1114 (2012)
Lin, T., RoyChowdhury, A., Maji, S.: Bilinear CNN models for fine-grained visual recognition. In: ICCV, pp. 1449–1457 (2015)
Ojala, T., Pietikäinen, M., Mäenpää, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. PAMI 24(7), 971–987 (2002)
Peng, K., Chen, T.: Cross-layer features in convolutional neural networks for generic classification tasks. In: ICIP, pp. 3057–3061 (2015)
Peng, K., Chen, T.: A framework of extracting multi-scale features using multiple convolutional neural networks. In: ICME, pp. 1–6 (2015)
Peng, K., Chen, T.: Toward correlating and solving abstract tasks using convolutional neural networks. In: WACV, pp. 1–9 (2016)
Puthenputhussery, A., Liu, Q., Liu, C.: Sparse representation based complete kernel marginal fisher analysis framework for computational art painting categorization. In: ECCV, vol. 9912, pp. 612–627 (2016)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Bengio, Y., LeCun, Y. (eds.) ICLR (2015)
Tan, W.R., Chan, C.S., Aguirre, H.E., Tanaka, K.: A deep convolutional network for fine-art paintings classification. In: ICIP, pp. 3703–3707 (2016)
Tseng, T., Chang, W., Chen, C., Wang, Y.F.: Style retrieval from natural images. In: ICASSP, pp. 1561–1565 (2016)
Yang, J., Zheng, W., Yang, Q., Chen, Y., Tian, Q.: Spatial-temporal graph convolutional network for video-based person re-identification. In: CVPR, pp. 3286–3296 (2020)
Yang, J., et al.: Historical context-based style classification of painting images via label distribution learning. In: 2018 ACM Multimedia Conference on Multimedia Conference, MM 2018, Seoul, Republic of Korea, 22–26 October 2018, pp. 1154–1162. ACM (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, Q., Feng, G. (2021). Image Style Recognition Using Graph Network and Perception Layer. In: Fang, L., Chen, Y., Zhai, G., Wang, J., Wang, R., Dong, W. (eds) Artificial Intelligence. CICAI 2021. Lecture Notes in Computer Science(), vol 13069. Springer, Cham. https://doi.org/10.1007/978-3-030-93046-2_48
Download citation
DOI: https://doi.org/10.1007/978-3-030-93046-2_48
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-93045-5
Online ISBN: 978-3-030-93046-2
eBook Packages: Computer ScienceComputer Science (R0)