Sage Journals: Discover world-class research

Abstract

The new media has changed the traditional way of information dissemination and formed a unique culture. The social impact of technological development has provided an unprecedented environment for art dissemination. In order to solve the problem that artworks including anime need to be labeled manually in the process of transmission, a media art design image classification method is proposed based on a visual biological neural network to classify the emotional style of artworks. In this paper, the ResNet101 neural network is improved, and the residual connection structure is changed by integrating the attention mechanism. This improvement provides rich global information for the model and improves the accuracy at the same time. To evaluate the proposed method, a data set of new media art designs and anime images is established. The experimental results show that the proposed methods in Acc, Precision, and Recall are 2.2%, 2.1%, and 2.0% higher than the original ResNet101, respectively. This method has made contributions to image classification in new media art design, and further accelerated the spread of art on the Internet.

Keywords

neural network new media art design ResNet101 image classification

Get full access to this article

View all access options for this article.

References

McCartney

Tynan

. Fashioning contemporary art: a new interdisciplinary aesthetics in art-design collaborations. J Vis Art Pract 2021; 20: 143–162.

Peppler

. Media arts: arts education for a digital age. Teach Coll Rec 2010; 112: 2118–2153.

Clark

. On the social history of art. In: Frascina

(ed). Modern art and modernism: a critical anthology. New York, NY: Routledge, 2018, pp. 249–258.

Rawat

Wang

. Deep convolutional neural networks for image classification: a comprehensive review. Neural Comput 2017; 29: 2352–2449.

Liakos

Busato

Moshou

, et al. Machine learning in agriculture: a review. Sensors (Peterb, NH) 2018; 18: 2674.

Chauhan

Dahiya

Sharma

. Problem formulations and solvers in linear SVM: a review. Artif Intell Rev 2019; 52: 803–855.

Dadi

Pillutla

. Improved face recognition rate using HOG features and SVM classifier. IOSR J Electron Commun Eng 2016; 11: 34–44.

Hamdan

Sathesh

. Hamdan Yasir Babiker Construction of statistical SVM based recognition model for handwritten character recognition. J Inf Technol 2021; 3: 92–107.

Guo

Liu

Oerlemans

, et al. Deep learning for visual understanding: a review. Neurocomputing 2016; 187: 27–48.

10.

Krizhevsky

Sutskever

Hinton

. Imagenet classification with deep convolutional neural networks. Commun ACM 2017; 60: 84–90.

11.

Simonyan

Zisserman

. Very deep convolutional networks for large-scale image recognition. arXiv 2014. Available from: https://arxiv.org/abs/1409.1556

12.

Zhang

Ren

, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 01 June 2016, pp. 770–778.

13.

Chollet

. Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017, pp. 1251–1258.

14.

Niu

Zhong

. A review on the attention mechanism of deep learning. Neurocomputing 2021; 452: 48–62.

15.

Wang

Girshick

Gupta

, et al. Non-local neural networks. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, 18–23 June 2018, pp. 7794–7803.

16.

Huang

Wang

Huang

, et al. Ccnet: criss-cross attention for semantic segmentation. In: Proceedings of the IEEE/CVF international conference on computer vision, Seoul, Korea (South), 27 October–2 November 2019, pp. 603–612.

17.

Liu

Dong

. G-ResNet: improved ResNet for brain tumor classification. In: Neural Information Processing: 26th International Conference, ICONIP 2019, 12–15 December 2019, Sydney, NSW, Australia, pp. 535–545.

18.

Ronneberger

Fischer

Brox

. U-net: convolutional networks for biomedical image segmentation. In: Navab

Hornegger

Wells

, et al. (eds). Medical Image Computing and Computer-Assisted Intervention, MICCAI 2015. Cham: Springer, 2015, pp. 234–241.

19.

. An improved ResNet based on the adjustable shortcut connections. IEEE Access 2018; 6: 18967–18974.

20.

Peng

Huang

Chen

, et al. More trainable inception-ResNet for face recognition. Neurocomputing 2020; 411: 9–19.

21.

Lei

Chen

Zhang

, et al. NLRNet: an efficient nonlocal attention ResNet for pansharpening. IEEE Trans Geosci Rem Sens 2021; 60: 1–13.

22.

Zhou

. Attention based stack resnet for citywide traffic accident prediction. In: 2019 20th IEEE International Conference on Mobile Data Management (MDM), Hong Kong, China, 10–13 June 2019, pp. 369–370.

23.

Huang

Lei

Xing

, et al. Evaluation of pulmonary edema using ultrasound imaging in patients with COVID-19 pneumonia based on a non-local channel attention ResNet. Ultrasound Med Biol 2022; 48(5): 945–953.

24.

Lin

Goyal

Girshick

, et al. Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 22–29 October 2017. pp. 2980–2988.

A novel image classification in new media art design based on a visual neural network

Abstract

Keywords

Get full access to this article

References