计算机科学 ›› 2014, Vol. 41 ›› Issue (4): 314-318.

• 图形图像与模式识别 • 上一篇    

基于混合图像分割与梯度算法的发光物体图像重建技术研究

成丽君,张宇波,徐从富   

  1. 山西农业大学信息科学与工程学院 晋中030801;山西农业大学信息科学与工程学院 晋中030801;浙江大学计算机科学与技术学院 杭州310027
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然科学基金课题(11JJ6056)资助

Image Reconstruction Algorithm Based on Graph Cuts and Gradient-based Algorithms

CHENG Li-jun,ZHANG Yu-bo and XU Cong-fu   

  • Online:2018-11-14 Published:2018-11-14

摘要: 传统的图像重建算法存在光源分布不均以及噪声干扰等问题,导致图像重建效果差。针对该问题,提出了一种改进的混合图割算法和梯度算法的发光体图像重建技术。算法首先采用图像分割算法得到在未知先验条件的情况下的发光源情况;然后利用不同的梯度算法,根据重建状态得到发光源准确的分布情况;最后利用内部光源的多级网络提高计算速度和重建的准确性。仿真实验结果表明,本方法即使在存在检测噪声和模型结构误差的情况下,仍然能够得到很好的重建性能,具有较高的实际应用价值。

关键词: 图像重建,图像分割,梯度算法,模型结构误差

Abstract: Image reconstruction is a promising optical molecular imaging technique on the frontier of biomedical optics.In this paper,a generalized hybrid algorithm for image reconstruction was proposed based on graph cut algorithm and gradient-based algorithms.The graph cut algorithm is adopted to estimate a reliable source support without prior knowledge,and different gradient-based algorithms are sequentially used to acquire an accurate and fine source distribution according to the reconstruction status.Furthermore,multilevel meshes for the internal sources are used to speed up the computation and improve the accuracy of reconstruction.Numerical simulations were performed to validate this proposed algorithm and demonstrate its high performance in the multi-source situation even if the detection noises,optical property errors and phantom structure errors are involved in the forward imaging.

Key words: Image reconstruction,Graph cuts,Gradient-based algorithm,Phantom structure error

[1] Rudin M,Weissleder R.Molecular imaging in drug discovery and development[J].Nat.Rev.Drug Discovery,2003,2:123-131
[2] Ntziachristos V,Ripoll J,Wang L V,et al.Looking and listening to light:the evolution of whole-body photonic imaging[J].Nat.Biotechnol,2005,23:313-320
[3] 刘晨彬,潘颖,张海石,等.基于磁共振图像的脑瘤 MGMT 表达状况检测算法[J].浙江大学学报:工学版,2012,1:028
[4] 姚俊杰,胡刚,岳蜀华,等.用于荧光分子断层成像的小动物躯干部分三维表面轮廓重建研究[J].中国生物医学工程学报,2008,27(3):360-365
[5] Ma X,Tian J,Qin C,et al.Early detection of liver cancer based on bioluminescence tomography[J].Appl.Opt.,2011,50:1389-1395
[6] 任鸽,曹兴芹,杨勇.基于局部区域拟合模型的磁共振图像分割与偏移估计算法[J].计算机应用,2011,31(12):3350-3352
[7] Zhang B,Yang X,Qin C,et al.A trust region method in adaptive finite element framework for bioluminescence tomography[J].Opt.Express,2010,18:6477-6491
[8] Feng J,Jia K,Yan G,et al.An optimal permissible source region strategy for multispectral bioluminescence tomography[J].Opt.Express,2008,6:15640-15654
[9] Naser M A,Patterson M S.Bioluminescence tomography using eigenvectors expansion and iterative solution for the optimized permissible source region[J].Biomed.Opt.Express,2011,2:3179-3193
[10] Naser M A,Patterson M S.Algorithms for bioluminescencetomography incorporating anatomical information and reconstruction of tissue optical properties [J].Biomed.Opt.Express,2010,1:512-526
[11] 何炳蔚,陈志鹏,林东艺,等.融合 SFS 和主动视觉技术的未知物体重建方法[J].仪器仪表学报,2012,33(4):727-736
[12] Liu K,Tian J,Lu Y,et al.A fast bioluminescent source localization method based on generalized graph cuts with mouse model validations[J].Opt.Express,2010,18:3732-3745
[13] 李彬,欧陕兴,田联房,等.基于自适应自由变形法和梯度下降法的胸部多模医学图像配准[J].计算机应用研究,2009,26(10):100-107
[14] 陈晶,孔令富.基于计算网格的图像三维重建系统的设计[J].计算机工程与科学,2009,31(9):39-41
[15] 厉小润,朱洁尔,王晶,等.组合核支持向量机高光谱图像分类[J].浙江大学学报:工学版,2013,8:012
[16] 贺小伟.生物发光断层成像中光源重建逆问题研究[D].西安:西安电子科技大学,2011
[17] 熊黎丽,王国胤,龚勋.基于三维重建的人脸姿态估计[J].重庆邮电大学学报:自然科学版,2010,22(3):375-380

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!