Wang Jianfeng, Fan Jiawei, Zhang Xiaoyan, Qian Bao
College of Design, Hanyang University, Ansan 15588, Republic of Korea.
School of Physics and Electronic Engineering, Xinjiang Normal University, Urumqi 830054, China.
Biomimetics (Basel). 2025 Jul 22;10(8):482. doi: 10.3390/biomimetics10080482.
During the long-term preservation of murals, the degradation of mural image information poses significant challenges to the restoration and conservation of world cultural heritage. Currently, mural conservation scholars focus on image segmentation techniques for mural restoration and protection. However, existing image segmentation methods suffer from suboptimal segmentation quality. To improve mural image segmentation, this study proposes an efficient mural image segmentation method termed Adaptive Nonlinear Bernstein-guided Parrot Optimizer (ANBPO) by integrating an adaptive learning strategy, a nonlinear factor, and a third-order Bernstein-guided strategy into the Parrot Optimizer (PO). In ANBPO, First, to address PO's limited global exploration capability, the adaptive learning strategy is introduced. By considering individual information disparities and learning behaviors, this strategy effectively enhances the algorithm's global exploration, enabling a thorough search of the solution space. Second, to mitigate the imbalance between PO's global exploration and local exploitation phases, the nonlinear factor is proposed. Leveraging its adaptability and nonlinear curve characteristics, this factor improves the algorithm's ability to escape local optimal segmentation thresholds. Finally, to overcome PO's inadequate local exploitation capability, the third-order Bernstein-guided strategy is introduced. By incorporating the weighted properties of third-order Bernstein polynomials, this strategy comprehensively evaluates individuals with diverse characteristics, thereby enhancing the precision of mural image segmentation. ANBPO was applied to segment twelve mural images. The results demonstrate that, compared to competing algorithms, ANBPO achieves a 91.6% win rate in fitness function values while outperforming them by 67.6%, 69.4%, and 69.7% in PSNR, SSIM, and FSIM metrics, respectively. These results confirm that the ANBPO algorithm can effectively segment mural images while preserving the original feature information. Thus, it can be regarded as an efficient mural image segmentation algorithm.
在壁画的长期保存过程中，壁画图像信息的退化给世界文化遗产的修复和保护带来了重大挑战。目前，壁画保护学者专注于用于壁画修复和保护的图像分割技术。然而，现有的图像分割方法存在分割质量欠佳的问题。为了改进壁画图像分割，本研究通过将自适应学习策略、非线性因子和三阶伯恩斯坦引导策略集成到鹦鹉优化器（PO）中，提出了一种高效的壁画图像分割方法，称为自适应非线性伯恩斯坦引导鹦鹉优化器（ANBPO）。在ANBPO中，首先，为了解决PO全局探索能力有限的问题，引入了自适应学习策略。通过考虑个体信息差异和学习行为，该策略有效地增强了算法的全局探索能力，能够对解空间进行全面搜索。其次，为了缓解PO全局探索和局部开发阶段之间的不平衡，提出了非线性因子。利用其适应性和非线性曲线特性，该因子提高了算法逃离局部最优分割阈值的能力。最后，为了克服PO局部开发能力不足的问题，引入了三阶伯恩斯坦引导策略。通过纳入三阶伯恩斯坦多项式的加权特性，该策略全面评估具有不同特征的个体，从而提高壁画图像分割的精度。ANBPO被应用于分割12幅壁画图像。结果表明，与竞争算法相比，ANBPO在适应度函数值方面的胜率达到91.6%，同时在PSNR、SSIM和FSIM指标上分别比它们高出67.6%、69.4%和69.7%。这些结果证实，ANBPO算法能够在保留原始特征信息的同时有效地分割壁画图像。因此，可以将其视为一种高效的壁画图像分割算法。
