Multi-objective band selection algorithm based on NSGA-II for pattern segmentation of textile hyperspectral images
Source abstract
Abstract
China is the birthplace of silk weaving, possessing a rich heritage of silk artifacts. Textile patterns exhibit unique artistic value and carry profound historical and cultural significance. Through automated segmentation of the patterns, we can provide technical support for the preservation, inheritance, and innovative application of cultural heritage. Edges are critical for image segmentation. Hyperspectral images enable precise identification of material and dye variations via continuous narrow-band spectral resolution, overcoming the limitations of RGB images in low-contrast edge detection. However, the redundant bands adversely affect results. To address the issue, we propose the edge-oriented multi-objective optimization of the band selection (EOMOBS) algorithm. Furthermore, to overcome texture noise interference, insufficient spectral information utilization, edge breaks, and poor parameter adaptability in existing methods, we propose an improved Canny operator for the selected bands. When applied to textile pattern segmentation, the method achieves 93.74% PA and 73.19% IoU, significantly outperforming sixteen alternative methods.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Cultural Heritage Materials Analysis · Industrial Vision Systems and Defect Detection · Wood and Agarwood Research
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (48)
Show source-provided references
1. Zhang, Y., Zhao, H., Qi, L., Zhang, J. & Zhang, T. Research on the co-occurrence feature mining of the Qing dynasty embroidery patterns based on temporal multilayer networks. npj Herit. Sci. 13, 228 (2025).10.1038/s40494-025-01766-z ↗
2. Li, H., Liu, W. & Li, X. Construction of basic-element database for traditional Chinese culture in industrial design. Procedia Comput. Sci. 91, 1011–1017 (2016).10.1016/j.procs.2016.07.137 ↗
3. Meng, K. et al. Database construction and remodeling method on traditional Yi nationality patterns of China with the Gan model. npj Herit. Sci. 13, 181 (2025).10.1038/s40494-025-01707-w ↗
4. Kleynhans, T., Schmidt Patterson, C. M., Dooley, K. A., Messinger, D. W. & Delaney, J. K. An alternative approach to mapping pigments in paintings with hyperspectral reflectance image cubes using artificial intelligence. Herit. Sci. 8, 1–16 (2020).10.1186/s40494-020-00427-7 ↗
5. Zhao, H. et al. Dating of Jingdezhen blue and white porcelain based on transfer learning and imaging spectroscopy techniques. npj Herit. Sci. 13, 68 (2025).10.1038/s40494-025-01652-8 ↗
6. Zeng, Z. et al. Virtual restoration of ancient tomb murals based on hyperspectral imaging. Tech. Rep. 1 (2024).10.1186/s40494-024-01501-0 ↗
7. Herens, E., Defeyt, C., Walter, P. & Strivay, D. Discovery of a woman portrait behind la violoniste by Kees van Dongen through hyperspectral imaging. Herit. Sci. 5, 1–8 (2017).10.1186/s40494-017-0127-4 ↗
8. Zheng, Q. et al. Extraction method of Yuan blue and white porcelain pattern based on multi-scale retinex and histogram multi-peak threshold segmentation. Herit. Sci. 12, 211 (2024).10.1186/s40494-024-01324-z ↗
9. Yao, Q., Zhou, Y., Tang, C., Xiang, W. & Zheng, G. End-to-end hyperspectral image change detection based on band selection. IEEE Trans. Geosci. Remote Sens. 62, 1–14 (2024).
10. Ou, X., Wu, M., Tu, B., Zhang, G. & Li, W. Multi-objective unsupervised band selection method for hyperspectral images classification. IEEE Trans. Image Process. 32, 1952–1965 (2023).10.1109/TIP.2023.3258739 ↗
11. Wu, J. et al. A novel framework combining band selection algorithm and improved 3d prototypical network for tree species classification using airborne hyperspectral images. Comput. Electron. Agric. 219, 108813 (2024).10.1016/j.compag.2024.108813 ↗
12. Zhang, L., Wei, Y., Liu, J., Wu, J. & An, D. A hyperspectral band selection method based on sparse band attention network for maize seed variety identification. Expert Syst. Appl. 238, 122273 (2024).10.1016/j.eswa.2023.122273 ↗
13. Fu, B., Sun, X., Cui, C., Zhang, J. & Shang, X. Structure-preserved and weakly redundant band selection for hyperspectral imagery. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 17, 12490–12504 (2024).10.1109/JSTARS.2024.3425906 ↗
14. Yong, Z., Chun-lin, H., Xian-fang, S. & Xiao-yan, S. A multi-strategy integrated multi-objective artificial bee colony for unsupervised band selection of hyperspectral images. Swarm Evolut. Comput. 60, 100806 (2021).10.1016/j.swevo.2020.100806 ↗
15. Deb, K., Pratap, A., Agarwal, S. & Meyarivan, T. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evolut. Comput. 6, 182–197 (2002).10.1109/4235.996017 ↗
16. Ghamisi, P., Couceiro, M. S., Martins, F. M. & Benediktsson, J. A. Multilevel image segmentation based on fractional-order darwinian particle swarm optimization. IEEE Trans. Geosci. Remote Sens. 52, 2382–2394 (2013).10.1109/TGRS.2013.2260552 ↗
17. Zeng, S., Wang, Z., Huang, R., Chen, L. & Feng, D. A study on multi-kernel intuitionistic fuzzy c-means clustering with multiple attributes. Neurocomputing 335, 59–71 (2019).10.1016/j.neucom.2019.01.042 ↗
18. Tarabalka, Y., Chanussot, J. & Benediktsson, J. A. Segmentation and classification of hyperspectral images using watershed transformation. Pattern Recognit. 43, 2367–2379 (2010).10.1016/j.patcog.2010.01.016 ↗
19. Lv, Z. Y., Zhang, P., Benediktsson, J. A. & Shi, W. Z. Morphological profiles based on differently shaped structuring elements for classification of images with very high spatial resolution. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 7, 4644–4652 (2014).10.1109/JSTARS.2014.2328618 ↗
20. Ozturk, N. & Ozturk, S. Comparison of image segmentation methods. In 2018 International Conference on Artificial Intelligence and Data Processing (IDAP), 1–4 (IEEE, Malatya, 2018).10.1109/IDAP.2018.8620739 ↗
21. Yu, H. et al. Multiscale superpixel-level subspace-based support vector machines for hyperspectral image classification. IEEE Geosci. Remote Sens. Lett. 14, 2142–2146 (2017).10.1109/LGRS.2017.2755061 ↗
22. Ozturk, N. & Ozturk, S. A new image enhancement method based on segmentation. Eur. J. Sci. Technol. 975–981 (2021).
23. Ozturk, N. & Ozturk, S. A new effective hybrid segmentation method based on c–v and lgdf. Signal, Image, Video Process. 15, 1313–1321 (2021).10.1007/s11760-021-01862-0 ↗
24. Bai, J. et al. Hyperspectral image classification based on superpixel feature subdivision and adaptive graph structure. IEEE Trans. Geosci. Remote Sens. 60, 1–15 (2022).
25. Zhang, J. et al. Spiking-lstm: A novel hyperspectral image segmentation network for sclerotinia detection. Comput. Electron. Agric. 226, 109397 (2024).10.1016/j.compag.2024.109397 ↗
26. Martin, D. R., Fowlkes, C. C. & Malik, J. Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Trans. pattern Anal. Mach. Intell. 26, 530–549 (2004).10.1109/TPAMI.2004.1273918 ↗
27. Sun, G. et al. Gravitation-based edge detection in hyperspectral images. Remote Sens. 9, 592 (2017).10.3390/rs9060592 ↗
28. Lei, T., Fan, Y. & Wang, Y. Colour edge detection based on the fusion of hue component and principal component analysis. IET Image Process. 8, 44–55 (2014).10.1049/iet-ipr.2013.0062 ↗
29. Chen, M., Yi, S., Wu, L., Yin, H. & Chen, L. Highly robust thermal infrared and visible image registration with canny and phase congruence detection. Opt. Lasers Eng. 183, 108526 (2024).10.1016/j.optlaseng.2024.108526 ↗
30. Shang, X., Cui, C. & Sun, X. Spectral-spatial hypergraph-regularized self-representation for hyperspectral band selection. IEEE Geosci. Remote Sens. Lett. 20, 1–5 (2023).10.1109/LGRS.2023.3276055 ↗
31. Zhang, M., Gong, M. & Chan, Y. Hyperspectral band selection based on multi-objective optimization with high information and low redundancy. Appl. Soft Comput. 70, 604–621 (2018).10.1016/j.asoc.2018.06.009 ↗
32. Saqui, D., Saito, J. H., De Lima, D. C., Cura, L. M. D. V. & Ataky, S. T. M. Incorporated decision-maker-based multiobjective band selection for pixel classification of hyperspectral images. Adv. Electr. Compu. Eng. 19, 21–28 (2019).10.4316/AECE.2019.04003 ↗
33. Hu, P., Liu, X., Cai, Y. & Cai, Z. Band selection of hyperspectral images using multiobjective optimization-based sparse self-representation. IEEE Geosci. Remote Sens. Lett. 16, 452–456 (2018).10.1109/LGRS.2018.2872540 ↗
34. Wan, Y., Zhong, Y., Ma, A. & Zhang, L. Hyperspectral remote sensing image band selection via multi-objective sine cosine algorithm. In IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium, 3796–3799 (IEEE, Yokohama, 2019).10.1109/IGARSS.2019.8898050 ↗
35. Zhao, H., Bruzzone, L., Guan, R., Zhou, F. & Yang, C. Spectral-spatial genetic algorithm-based unsupervised band selection for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 59, 9616–9632 (2021).10.1109/TGRS.2020.3047223 ↗
36. Song, M., Liu, S., Xu, D. & Yu, H. Multiobjective optimization-based hyperspectral band selection for target detection. IEEE Trans. Geosci. Remote Sens. 60, 1–22 (2022).
37. Canny, J. A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 8, 679–698 (1986).10.1109/TPAMI.1986.4767851 ↗
38. Ozturk, N. & Ozturk, S. Efficient and natural image fusion method for low-light images based on active contour model and adaptive gamma correction. Multimed. Tools Appl. 83, 48437–48456 (2024).10.1007/s11042-023-17141-8 ↗
39. Xin, G., Ke, C. & Xiaoguang, H. An improved Canny edge detection algorithm for color image. In IEEE 10th International Conference on Industrial Informatics, 113–117 (IEEE, Beijing, 2012).10.1109/INDIN.2012.6301061 ↗
40. Xuan, L. & Hong, Z. An improved Canny edge detection algorithm. In 2017 8th IEEE international conference on software engineering and service science (ICSESS), 275–278 (IEEE, Beijing, 2017).10.1109/ICSESS.2017.8342913 ↗
41. Minaee, S. et al. Image segmentation using deep learning: A survey. IEEE Trans. Pattern Anal. Mach. Intell. 44, 3523–3542 (2021).
42. Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, 234–241 (Springer, Cham, 2015).10.1007/978-3-319-24574-4_28 ↗
43. Zhao, H., Shi, J., Qi, X., Wang, X. & Jia, J. Pyramid scene parsing network. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2881–2890 (IEEE, Honolulu, 2017).10.1109/CVPR.2017.660 ↗
44. Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F. & Adam, H. Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European conference on computer vision (ECCV), 801–818 (Springer, Munich, 2018).10.1007/978-3-030-01234-2_49 ↗
45. Al-Khafaji, S. L., Zhou, J., Bai, X., Qian, Y. & Liew, A. W.-C. Spectral-spatial boundary detection in hyperspectral images. IEEE Trans. Image Process. 31, 499–512 (2021).10.1109/TIP.2021.3131942 ↗
46. Soria, X., Li, Y., Rouhani, M. & Sappa, A. D. Tiny and efficient model for the edge detection generalization. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 1364–1373 (IEEE, Paris, 2023).10.1109/ICCVW60793.2023.00147 ↗
47. Su, Z. et al. Pixel difference networks for efficient edge detection. In Proceedings of the IEEE/CVF international conference on computer vision, 5117–5127 (IEEE, Montreal, 2021).10.1109/ICCV48922.2021.00507 ↗
48. Soria, X., Sappa, A., Humanante, P. & Akbarinia, A. Dense extreme inception network for edge detection. Pattern Recognit. 139, 109461 (2023).10.1016/j.patcog.2023.109461 ↗