Design and Implementation of a Cross-Cultural Pattern Classification System Based on ResNet18

Alina Andreeva; Zhenning Li; Wenjie Tang; Chaofan Yue; Xinlei  Cao; Xiang Zhang; Xiangyu  Li

doi:10.62177/jaet.v3i2.1367

Authors

Alina Andreeva The Bonch-Bruevich Saint Petersburg State University of Telecommunications
Zhenning Li D.F. Ustinov Baltic State Technical University "VOENMEH"
Wenjie Tang D.F. Ustinov Baltic State Technical University "VOENMEH"
Chaofan Yue ITMO University
Xinlei Cao Nanjing Forestry University
Xiang Zhang ITMO University
Xiangyu Li Shanghai Jiao Tong University

DOI:

https://doi.org/10.62177/jaet.v3i2.1367

Keywords:

Transfer Learning, ResNet18, Cross-cultural Pattern Classification, Cultural Heritage Digitization, Convolutional Neural Network, Data Augmentation, Image Classification

Abstract

The automatic recognition of traditional cultural patterns from China, Japan, and Korea poses a challenging cross-cultural image classification problem, compounded by high intra-class stylistic diversity, inter-cultural iconographic overlap, and the scarcity of annotated training data. We propose a lightweight transfer learning framework in which a ResNet18 backbone pre-trained on ImageNet is fully frozen and a compact three-class fully connected head comprising only 2,565 trainable parameters is appended and optimized for the target task, together with a stochastic data augmentation pipeline combing random resized cropping, horizontal flipping, rotation, and Colour jitter. A purposebuilt benchmark of 750 balanced images spanning Chinese, Japanese, and Korean traditional patterns is constructed and partitioned following a 70:15:15 ratio. Comprehensive evaluation against five competing architectures (VGG16, MobileNetV2, EfficientNet-B0, DenseNet121, and a from-scratch SimpleCNN baseline) under identical training conditions demonstrates that the proposed method achieves 87.61% test accuracy and an F1-score of 0.8746, outperforming SimpleCNN by 8.85 percentage points while requiring over four orders of magnitude fewer trainable parameters than VGG16. Controlled ablation experiments reveal that data augmentation contributes the largest single performance gain of 22.00 percentage points, followed by ImageNet pre-training at 11.61 percentage points. Per-class analysis shows that Korean patterns are most reliably discriminated (F1 = 0.900), Japanese patterns achieve the highest recall (0.949), and Chinese patterns pose the greatest challenge (recall = 0.765) owing to their broad stylistic range and historical iconographic diffusion into neighboring traditions. These findings establish that a frozen-backbone transfer learning strategy with targeted augmentation provides an efficient and practically deployable solution for cross-cultural heritage pattern recognition under realistic computational constraints.

Downloads

Download data is not yet available.

References

Zhao Liu. (2024). The construction of a digital dissemination platform for the intangible cultural heritage using convolutional neural network models. Heliyon, 10(24), e40854. https://doi.org/10.1016/j.heliyon.2024.e40854 DOI: https://doi.org/10.1016/j.heliyon.2024.e40854

Liu, Y., Cheng, P., & Li, J. (2023). Application interface design of Chongqing intangible cultural heritage based on deep learning. Heliyon, 9(11), e09450. https://doi.org/10.1016/j.heliyon.2023.e22166 DOI: https://doi.org/10.1016/j.heliyon.2023.e22242

Fu, X. (2021). Research and application of ancient Chinese pattern restoration based on deep convolutional neural network. Computational Intelligence and Neuroscience, 2021, 2691346. https://doi.org/10.1155/2021/2691346 DOI: https://doi.org/10.1155/2021/2691346

Ji, J., Lao, Y., & Huo, L. (2024). Convolutional neural network application for supply-demand matching in Zhuang ethnic clothing image classification. Scientific Reports, 14, 4082. https://doi.org/10.1038/s41598-024-64082-9 DOI: https://doi.org/10.1038/s41598-024-64082-9

Belhi, A., Ahmed, H. O., Alfaqheri, T., Bouras, A., Sadka, A. H., & Foufou, S. (2021). Study and evaluation of pre-trained CNN networks for cultural heritage image classification. In Advances in Intelligent Systems and Computing (pp. 51-67). Springer. https://doi.org/10.1007/978-3-030-66777-1_3 DOI: https://doi.org/10.1007/978-3-030-66777-1_3

Chen, B. (2022). Classification of artistic styles of Chinese art paintings based on the CNN model. Computational Intelligence and Neuroscience, 2022, 4520913. https://doi.org/10.1155/2022/4520913 DOI: https://doi.org/10.1155/2022/4520913

Tan, Y. (2022). Feature recognition and style transfer of painting image using lightweight deep learning. Computational Intelligence and Neuroscience, 2022, 1478371. https://doi.org/10.1155/2022/1478371 DOI: https://doi.org/10.1155/2022/1478371

Lou, J., Shavetov, S., Wen, X., Li, Z., Zhang, X., & Yuan, C. (2026). Deep learning-based instance segmentation: A comprehensive review of algorithms, challenges, and future directions. The Visual Computer, 42(6), 235. DOI: https://doi.org/10.1007/s00371-026-04444-8

Yang, S., Xiao, W., Zhang, M., Guo, S., Zhao, J., & Shen, F. (2022). Image data augmentation for deep learning: A survey. arXiv preprint arXiv:2204.08610.

Alomar, K., Aysel, H. I., & Cai, X. (2023). Data augmentation in classification and segmentation: A survey and new strategies. Journal of Imaging, 9(2), 46. https://doi.org/10.3390/jimaging9020046 DOI: https://doi.org/10.3390/jimaging9020046

Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345-1359. https://doi.org/10.1109/TKDE.2009.191 DOI: https://doi.org/10.1109/TKDE.2009.191

Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A. C., & Fei-Fei, L. (2015). ImageNet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211-252. https://doi.org/10.1007/s11263-015-0816-y DOI: https://doi.org/10.1007/s11263-015-0816-y

Qi, X.-Z., He, X.-M., Chen, S.-W., & Hai, T. (2024). A framework of evolutionary optimized convolutional neural network for classification of Shang and Chow dynasties bronze decorative patterns. PLOS ONE, 19(10), e0293517. https://doi.org/10.1371/journal.pone.0293517 DOI: https://doi.org/10.1371/journal.pone.0293517

Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(pp. 4510-4520). https://doi.org/10.1109/CVPR.2018.00474 DOI: https://doi.org/10.1109/CVPR.2018.00474

Tan, M., & Le, Q. V. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. In Proceedings of the 36th International Conference on Machine Learning (ICML) (pp. 6105-6114).

He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 770-778). https://doi.org/10.1109/CVPR.2016.90 DOI: https://doi.org/10.1109/CVPR.2016.90

Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.

Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.

Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the 32nd International Conference on Machine Learning (ICML) (pp. 448-456).

Gu, C., & Lee, M. (2024). Deep transfer learning using real-world image features for medical image classification, with a case study on pneumonia X-ray images. Applied Sciences, 14(11), 4083. https://doi.org/10.3390/app14114083 DOI: https://doi.org/10.3390/bioengineering11040406

Lin, M., Chen, Q., & Yan, S. (2013). Network in network. arXiv preprint arXiv:1312.4400.

Cheng, W., Liu, Z., & Li, X. (2026). Enhanced lightweight architecture for real-time detection of agricultural pests and diseases. Computers, Materials & Continua, 87(2), 2459-2497. https://doi.org/10.32604/cmc.2025.074250 DOI: https://doi.org/10.32604/cmc.2025.074250

Yuan, C., Liu, Z., Li, X., Zhou, X., Wang, D., Fan, Y., Sun, X., & Tian, Z. (2025). A dynamic weighted ensemble learning framework for cardiovascular risk prediction in type 2 diabetes: A comparative study with SHAP-based interpretability. Scientific Reports. DOI: https://doi.org/10.1038/s41598-025-28786-w

Liu, Z., Yuan, C., Liu, H., Li, X., Liu, S., Zhou, X., & Tian, Z. (2026). MSTDP: A multi-scale temporal deep learning framework for just-in-time software defect prediction with cross-attention fusion. Journal of King Saud University Computer and Information Sciences. DOI: https://doi.org/10.1007/s44443-025-00401-y

Yang, J., Govindarajan, V., Arif, S., Xu, X., Kallel, M., Shaikh, Z. A., Liu, Z., Yuan, C., & Por, L. Y. (2025). SwarmSense-DNN: A trustworthy and decentralized neural framework for proactive anomaly defense in consumer IoT. IEEE Transactions on Consumer Electronics. DOI: https://doi.org/10.1109/TCE.2025.3634160

Wang, Y., Zhang, H., Yuan, C., Li, X., & Jiang, Z. (2025). An efficient scheduling method in supply chain logistics based on network flow. Processes, 13(4), 969. DOI: https://doi.org/10.3390/pr13040969

Xu, L., Yuan, C., & Jiang, Z. (2025). Multi-strategy enhanced secret bird optimization algorithm for solving obstacle avoidance path planning for mobile robots. Mathematics, 13(5), 717. DOI: https://doi.org/10.3390/math13050717

Zhang, Y., Yuan, C., Wang, L., Chen, Y., Xing, Y., & Sun, Y. (2025). The structure-preserving spectral graph neural network for dual kinase inhibitors and synergy scoring in gastric cancer. npj Digital Medicine. DOI: https://doi.org/10.1038/s41746-025-02240-7

Yuan, C., Cai, Y., Que, H., Pei, Y., Zhang, X., Xie, J., Zhang, Q., Mu, L., & Qiao, F. (2026). KA-IHO: A kinematic-aware improved hippo optimization algorithm for collision-free mobile robot path planning in complex grid environments. Sensors, 26(8), 2416. DOI: https://doi.org/10.3390/s26082416

Yi, X., Yuan, C., Tian, Z., Wu, X., Wu, H., & Liu, L. (2026). BiCoMT: Bidirectional coupling modulation transformer with multi-scale for spatio-temporal traffic flow prediction. Journal of King Saud University Computer and Information Sciences. DOI: https://doi.org/10.1007/s44443-026-00714-6

Yuan, C., Wei, T., Li, C., Yi, X., Liu, S., Zhang, Z., Cai, Y., & Du, X. (2026). PaperOrchestrator: An LLM-orchestrated multi-agent pipeline for automated end-to-end scientific paper writing. Journal of King Saud University Computer and Information Sciences. DOI: https://doi.org/10.1007/s44443-026-00708-4

Tian, Z., Lin, Z., Yuan, C., Prajapat, S., Yang, J., & Yee, L. (2026). Consumer-electronics-oriented safe interaction-aware motion planning for ramp driving with perception uncertainty quantification. IEEE Transactions on Consumer Electronics. DOI: https://doi.org/10.1109/TCE.2026.3675966