Feature enhancement and attention mechanism fusion method for Cantonese embroidery image detection based on YOLOv8
Source abstract
Abstract
Cantonese embroidery images are difficult to recognize accurately because of significant differences in their morphologies and complex backgrounds. In this paper, a dedicated Cantonese embroidery image dataset is constructed, and an improved YOLOv8 detection method is proposed for the accurate detection of objects in Cantonese embroidery images. By integrating a feature enhancement module and the large separable kernel attention (LSKA) mechanism, the method strengthens its capacity for identifying key texture regions, enhances feature extraction in complex backgrounds, and optimizes performance through lightweight design and the WIoU loss function. The experimental results show that the method achieves a detection accuracy of 98.5%, with mAP and F1 scores improved by 0.7% and 1.37%, respectively, compared with those of the original model, and the model size is reduced by 5.12%. This provides an effective solution for the automated detection of intangible cultural heritage embroidery and the recognition of other heritage artifacts.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Visual Attention and Saliency Detection · Industrial Vision Systems and Defect Detection · Advanced Image Fusion Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (33)
Show source-provided references
1. United Nations Educational, Scientific and Cultural Organization (UNESCO). Convention for the Safeguarding of the Intangible Cultural Heritage https://unesdoc.unesco.org/ark:/48223/pf0000186627 (2003).
2. Huang, H. A Study on the Aesthetic Characteristics of Cantonese embroidery from the Perspective of Lingnan Culture. (Master’s thesis, Guangzhou University, Guangzhou, 2017)
3. Jurie, F. & Dhome, M. A simple and efficient template matching algorithm. Proc. Eighth IEEE Int. Conf. Computer Vis. ((ICCV)) 2, 544–549 (2001).10.1109/ICCV.2001.937673 ↗
4. Zou, Z., Chen, K., Shi, Z., Guo, Y. & Ye, J. Object detection in 20 years: A survey. Proc. IEEE 111, 257–276 (2023).10.1109/JPROC.2023.3238524 ↗
5. Liu, Y. X., et al. Image inpainting for embroidery based on improved deep convolutional generative adversarial networks. Laser & Optoelectronics Progress, 60: 2010005–2010005-11, (2023).10.3788/LOP223060 ↗
6. Sharma, D., Dhiman, C. & Kumar, D. Control with style: Style embedding-based variational autoencoder for controlled stylized caption generation framework. IEEE Trans. Cogn. Dev. Syst. 16, 2032–2042 (2024).10.1109/TCDS.2024.3405573 ↗
7. Sharma, D. XGL-T transformer model for intelligent image captioning. Multimed. Tools Appl. 83, 4219–4240 (2024).10.1007/s11042-023-15291-3 ↗
8. Gu, J. et al. Recent advances in convolutional neural networks. Pattern Recognit. 77, 354–377 (2018).10.1016/j.patcog.2017.10.013 ↗
9. Girshick, R., Donahue, J., Darrell, T. & Malik, J. Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 580-587 (2014).10.1109/CVPR.2014.81 ↗
10. Ren, S., He, K., Girshick, R. & Sun, J. Faster R-CNN: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28 (2015).
11. He, K., Gkioxari, G., Dollar, P. & Girshick, R. Mask R-CNN. Proceedings of the IEEE international conference on computer vision, 2961–2969 (2017).10.1109/ICCV.2017.322 ↗
12. Redmon, J., Divvala, S., Girshick, R. & Farhadi, A. You only look once: Unified, real-time object detection. Proceedings of the IEEE conference on computer vision and pattern recognition, 779–788. (IEEE, 2016).10.1109/CVPR.2016.91 ↗
13. Liu, W. et al. SSD: Single Shot MultiBox Detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds) Computer Vision – ECCV 2016. Lecture Notes in Computer Science, 9905. (Springer, Cham, 2016).10.1007/978-3-319-46448-0_2 ↗
14. Tan, M., Pang, R. & Le, Q. V. EfficientDet: Scalable and efficient object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 10781–10790 (2020).10.1109/CVPR42600.2020.01079 ↗
15. He, K., Zhang, X., Ren, S. & Sun, J. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37, 1904–1916 (2015).10.1109/TPAMI.2015.2389824 ↗
16. Girshick, R. Fast R-CNN. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 1440–1448 (2015).10.1109/ICCV.2015.169 ↗
17. Zhao H. X. Classification and recognition algorithm of embroidery images based on deep learning. (Master’s thesis, Qinghai Normal University, Qinghai 2021).
18. Rizki, Y., Medikawati Taufiq, R., Mukhtar, H., Apri Wenando, F. & Al Amien, J. Comparison between faster R-CNN and CNN in recognizing weaving patterns. In 2020 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS), 81-86 (IEEE, 2020).10.1109/ICIMCIS51567.2020.9354324 ↗
19. Sun, K.-K., Huang, J.-W., Yuan, Y.-Y. & Chen, M.-Y. Classification and recognition of the nantong blue calico pattern based on deep learning. J. Engineered Fibers Fabr. 19, 15589250241270618 (2024).10.1177/15589250241270618 ↗
20. Zhu, J. J. & Zhu, C. Research on the innovative application of shen embroidery cultural heritage based on convolutional neural network. Sci. Rep. 14, 9574 (2024).10.1038/s41598-024-60121-7 ↗
21. Zhu C. Y., Xue, B., Zhu, J. J., & Huang W. J. Research on image recognition of nantong shen embroidery intangible cultural heritage based on improved mobile net V3. Preprint at https://doi.org/10.21203/rs.3.rs-5300929/v1 (2024).10.21203/rs.3.rs-5300929/v1 ↗
22. Sharma, D., Dhiman, C. & Kumar, D. UnMA-CapSumT: Unified and multi-head attention-driven caption summarization transformer. https://doi.org/10.48550/arXiv.2412.11836 (2024).10.48550/arXiv.2412.11836 ↗
23. Wang, J. H., Chen, H. Y. & Chen, Y. Research on pattern image recognition model introducing attention mechanism. Print. Digital Media Technol. Res. 2, 46–53 (2024).
24. Howard, A. G. et al. MobileNets: Efficient convolutional neural networks for mobile vision applications. https://doi.org/10.48550/arXiv.1704.04861 (2017).10.48550/arXiv.1704.04861 ↗
25. Lau, K. W., Po, L.-M. & Rehman, Y. A. U. Large separable kernel attention: Rethinking the large kernel attention design in CNN. Expert Syst. Appl. 236, 121352 (2024).10.1016/j.eswa.2023.121352 ↗
26. Tong, Z., Chen, Y., Xu, Z. & Yu, R. Wise-IoU: Bounding box regression loss with dynamic focusing mechanism. https://doi.org/10.48550/arXiv.2301.10051 (2023).10.48550/arXiv.2301.10051 ↗
27. Cao, W. & Meng, X. D. Design of Cantonese embroidery pattern elements in silk cultural and creative products. Screen Print. 2, 1–4 (2023).
28. Sohan, M., Sai Ram, T. & Reddy, C. V. R. A Review on YOLOv8 and Its Advancements. International Conference on Data Intelligence and Cognitive Informatics. 529–545 (Springer, Singapore, 2024).10.1007/978-981-99-7962-2_39 ↗
29. Ali, M., Javaid, M., Noman, M., Fiaz, M. & Khan, S. Fanet: Feature amplification network for semantic segmentation in cluttered background. 2024 IEEE International Conference on Image Processing (ICIP). 2592–2598 (IEEE, 2024).10.1109/ICIP51287.2024.10647349 ↗
30. Woo, S., Park, J., Lee, J.-Y. & Kweon, I. S. CBAM: Convolutional block attention module. Proceedings of the European conference on computer vision (ECCV). 3-19 (2018).10.1007/978-3-030-01234-2_1 ↗
31. Hu, J., Shen, L. & Sun, G. Squeeze-and-excitation networks. Proceedings of the IEEE conference on computer vision and pattern recognition. 7132-7141 (2018).10.1109/CVPR.2018.00745 ↗
32. Hou, Q., Zhou, D. & Feng, J. Coordinate attention for efficient mobile network design. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR). 13713-13722 (IEEE, 2021).10.1109/CVPR46437.2021.01350 ↗
33. Wang, Q. et al. ECA-net: Efficient channel attention for deep convolutional neural networks. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 11531–11539 (IEEE, 2020).10.1109/CVPR42600.2020.01155 ↗