Dual-energy CT image fusion algorithm for composite materials
-
摘要: 针对复合材料在X射线单一能量下CT图像对比度低、细节信息不清晰等问题,提出一种基于生成对抗网络的双能CT图像融合方法,用于融合高低能量条件下的图像。该网络由一个生成器和两个判别器组成,生成器用于提取CT图像的细节信息,两个判别器用于区分融合CT图像和高低能CT图像之间的结构差异,判断数据的真假。通过端到端模型的对抗训练完成融合模型的构建,最后生成包含高低能信息的融合CT图像。试验结果表明,提出的基于生成对抗网络的双能CT图像融合算法,很好地突破了单能X射线CT成像的局限性,融合后的双能CT图像细节更加丰富,有利于复合材料关键图像信息的判读。Abstract: In order to solve the problems of low contrast and unclear detail information of composite CT images under single X-ray energy, a dual-energy CT image fusion method based on generative adversarial network was proposed to fuse images under low and high energy condition. The network consists of a generator and two discriminators. The generator was used to extract the details of CT images. Meanwhile, two discriminators were used to distinguish the structural differences between fusion CT images and high-low energy CT images, and to distinguish the authenticity of data. The fusion model was established through the adversarial training of the end to end model, and finally the fusion CT image containing high and low energy information was generated. The experimental results show that the proposed dual-energy image fusion algorithm based on generative adversarial network solves the limitations of single-energy CT imaging well, and the fused dual-energy CT image has more details, which was beneficial to the interpretation of key image information of composite materials.
-
Keywords:
- dual-energy CT /
- composite material /
- image fusion /
- generative adversarial network
-
-
[1] IZUMI S, KAMATA S, SATOH K, et al.High energy X-ray computed tomography for industrial applications[J].IEEE Transactions on Nuclear Science, 1993, 40(2):158-161.
[2] 孙鸿祥.大型工业CT在摇枕、侧架无损检测中的应用[J].中国仪器仪表, 2011(10):49-52. [3] 丁国富.大型高能工业CT在固体火箭发动机检测方面的应用[J].CT理论与应用研究, 2005, 14(3):35-39. [4] 孟博, 郑岚, 刘硕.CT安检探测技术的特点及优势[J].中国安防, 2021(4):78-81. [5] 李保磊, 张萍宇.国外CT型安检设备与技术发展[J].中国安防, 2013(6):84-87. [6] 黄河, 叶文华, 熊田忠, 等.基于双能X射线透射的区域分块废有色金属识别算法[J].机械制造与自动化, 2019, 48(4):26-29. [7] 朱炼, 孙枫, 夏芳莉, 等.图像融合研究综述[J].传感器与微系统, 2014, 33(2):14-18. [8] 周渝人, 耿爱辉, 张强, 等.基于压缩感知的红外与可见光图像融合[J].光学精密工程, 2015, 23(3):855-863. [9] HERRINGTON W F, HORN B K P, MASAKI I.Application of the discrete Haar wavelet transform to image fusion for nighttime driving[C]//IEEE Proceedings.Intelligent Vehicles Symposium.Las Vegas, NV, USA:IEEE, 2005.
[10] 胡春光, 靳丽媛, 邹晶, 等.基于小波融合的双能X射线图像增强算法[J].纳米技术与精密工程, 2016, 14(6):429-433. [11] 杨民, 吴美金, 魏东波, 等.双能透照模式下涡轮叶片DR图像融合方法[J].北京航空航天大学学报, 2011, 37(12):1494-1497. [12] 杨霈, 董秋影, 杨民.基于小波变换的双能DR图像融合[J].无损检测, 2008, 30(7):430-433. [13] LIU G, JING Z L, LI J X, et al.Image fusion based on estimation theory[C]//Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat.No.04EX826).Shanghai, China:IEEE, 2005.
[14] 张淑梅, 刘跃新.基于均值聚类多小波图像融合算法研究[J].计算机仿真, 2011, 28(11):242-245. [15] TU T M, HUANG P S, HUNG C L, et al.A fast intensity-hue-saturation fusion technique with spectral adjustment for IKONOS imagery[J].IEEE Geoscience and Remote Sensing Letters, 2004, 1(4):309-312.
[16] YANG B, LI S T.Pixel-level image fusion with simultaneous orthogonal matching pursuit[J].Information Fusion, 2012, 13(1):10-19.
[17] SUN K S, LIU F S. Research on the multi-focus image fusion method based on the second-generation Curvelet transformation[J]. Applied Mechanics and Materials, 2014, 687:3624-3627.
[18] YIN H T, LI S T, FANG L Y.Simultaneous image fusion and super-resolution using sparse representation[J].Information Fusion, 2013, 14(3):229-240.
[19] 蔺素珍, 韩泽.基于深度堆叠卷积神经网络的图像融合[J].计算机学报, 2017, 40(11):2506-2518.
计量
- 文章访问数: 5
- HTML全文浏览量: 0
- PDF下载量: 5