古铜镜X光生成对抗融合中的优化策略  

Optimization Strategy for X-Ray Generation and Countermeasure Fusion of Bronze Mirror

作　　者：吴萌[1] 王姣 相建凯 Wu Meng;Wang Jiao;Xiang Jiankai(College of Information and Control Engineering,Xi’an University of Architecture and Technology,Xi’an 710055,Shaanxi,China;Shaanxi Institute for the Preservation of Cultural Heritage,Xi’an 710075,Shaanxi,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]陕西省文物保护研究院,陕西西安710075

出　　处：《激光与光电子学进展》2023年第2期456-465,共10页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(61701388);陕西省自然科学基础研究计划(2018JM6080);西安市科技局项目(GXYD10.1)。

摘　　要：锈蚀覆盖的古铜镜在非接触探伤检测中,因镜缘与镜心厚度各异,X光成像无法呈现完整的病害信息。以古铜镜X光信号为输入,搭建生成对抗融合网络。针对L_(2)损失和梯度算子所导致的重构模糊、纹饰和裂痕等多尺度特征细节表达等问题,设计了能够增强古铜镜X光信息融合效果的优化策略。通过添加L_(2,1/2)损失正则化生成器的特征学习过程,改善L_(2)损失生成信息平滑的现象;定义拉普拉斯L_(tex)纹饰损失,加强训练网络对纹饰和病害的抽取效果;在训练网络中加入多尺度特征融合模块,提高细节信息生成质量。通过与7种融合方法进行实验对比,所提算法在5组对照数据中仅2组的交叉熵值略差,其余信息熵、平均梯度、空间频率、联合熵和非参考特征互信息值均取得最优,可有效呈现古铜镜X光探伤检测信息。During the non-contact flaw detection of a rust-covered bronze mirror,X-ray imaging typically fails to reveal the extent of damage due to the thickness difference between the mirror edge and core.In this study,the X-ray signal from a bronze mirror was used as an input to construct a generative confrontation fusion network.An optimization strategy that enhances the bronze mirror X-ray information fusion was designed to address the reconstruction blur caused by the L_(2) loss and gradient operator,and the expression of multiscale feature details,such as textures and cracks.By utilizing the feature learning process of the L_(2,1/2) loss regularization generator,the smoothing of the data that was generated using the L_(2) loss was improved;moreover,the Laplacian L_(tex) pattern loss was defined to strengthen the effect of training network on the extraction of decorations and diseases.Furthermore,a multiscale feature fusion module was added to the training network to improve the quality of the generated information.Thus,considering the experimental comparison involving seven fusion methods,the cross entropy value of the proposed algorithm in two of the five groups is poor.However,the values are optimal in the control data,including entropy,average gradient,spatial frequency,joint entropy,and non-reference feature mutual information.This can effectively reveal the detection information of the bronze mirror during X-ray flaw detection.

关 键 词：X光图像 生成对抗网络 多尺度融合 L_(2 1/2)稀疏 拉普拉斯算子 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]