基于直觉模糊集熵测度和显著特征检测的古铜镜X光图像融合  

X-ray image fusion for ancient bronze mirror based on intuitionistic fuzzy set entropy measure and salient feature detection

作　　者：吴萌[1,3] 张倩文 孙增国[2] 相建凯 郭歌 WU Meng;ZHANG Qianwen;SUN Zengguo;XIANG Jiankai;GUO Ge(College of Information and Control Engineering,Xi′an University of Architecture and Technology,Xi′an 710055,China;College of Computer Science,Shaanxi Normal University,Xi′an 710119,China;College of Institute for Interdisciplinary Innovation Research,Xi'an University of Architecture and Technology,Xi′a n 710055,China;Shaanxi Institute for the Preservation of Cultural Heritage,Xi’an 710075,China)

机构地区：[1]西安建筑科技大学信息与控制工程学院,陕西西安710055 [2]陕西师范大学计算机科学学院,陕西西安710119 [3]西安建筑科技大学交叉创新研究院,陕西西安710055 [4]陕西省文物保护研究院,陕西西安710075

出　　处：《光学精密工程》2025年第2期262-281,共20页Optics and Precision Engineering

基　　金：国家重点研发计划资助项目(No.2023YFC3803900);国家自然科学基金资助项目(No.62377033);西安建筑科技大学交叉研究培育专项资助项目(No.X2022082,No.X20230085)。

摘　　要：针对被锈蚀覆盖的古铜镜因镜缘与镜心区域厚度不均,单能X射线无法检测出完整的纹饰和病害信息的问题,本文提出一种直觉模糊集熵测度和显著特征检测的古铜镜X光图像融合方法。首先,引入有效引导滤波对高能量X光图像的纹饰结构做对比度增强。接着,采用联合双边滤波和结构-纹理分解策略设计三个尺度分解模型,以提取不同能量X光图像的能量层、残差层和细节层信息。其次,能量层通过l1-max规则得到融合后的能量图像,残差层利用直觉模糊集熵测度构造小尺度纹理特征融合模块,细节层结合扩展差分高斯与空间频率增强算子构建复合型显著特征检测策略。最后,将能量融合图、残差融合图和细节融合图相加得到最终融合结果。实验结果表明,本文方法的6种客观评价指标AG,SF,SD,SCD,NAB/F和SSIM相较于对比方法分别平均提高了23.59%,22.99%,16.12%,42.55%,17.07%,20.54%,融合结果可以有效保留古铜镜清晰的纹饰细节和病害裂隙的关键特征,在对比度和结构保持等方面都优于其他对比方法。A fusion method was proposed to solve the problem that the single-energy X-ray cannot detect the complete decoration and disease information of the corroded ancient bronze mirror due to the uneven thickness of the mirror edge and the mirror center area.The method combined intuitionistic fuzzy set entropy measure and salient feature detection to fuse ancient bronze mirror X-ray images.Firstly,the effective guided filtering was introduced to enhance the contrast of the decorative structure of high-energy X-ray images.Secondly,a three-scale decomposition model was designed by using joint bilateral filtering and structure-texture decomposition strategy.The model extracted the energy layer,residual layer and detail layer information of different energy X-ray images.Then,the energy layer obtained the fused energy image through the l1-max rule.The residual layer used the intuitionistic fuzzy set entropy measure to construct a small-scale texture feature fusion module.And the detail layer combined the extended difference-of-Gaussians and spatial frequency enhancement operator to construct a composite saliency feature detection strategy.Finally,the energy fusion map,residual fusion map,and detail fusion map were added to obtain the final fusion result.The experimental results show that the six objective evaluation indexes AG,SF,SD,SCD,N AB/Fand SSIM of this method are improved by 22.19%,22.66%,15.01%,44.69%,17.07%,and 21.46%on average,respectively,compared with the other methods.The fusion results can effectively retain the clear decorative details of the ancient bronze mirror and the key features of the disease cracks.And it outperforms other comparison methods in terms of contrast and structure retention.

关 键 词：图像融合 边缘保持滤波 三尺度分解 纹理提取 直觉模糊集熵测度 显著特征检测 

分 类 号：TP394.1[自动化与计算机技术—计算机应用技术] TH691.9[自动化与计算机技术—计算机科学与技术]