Image fusion based on shearlet transform and region characteristics
-
摘要: 为了提高多模医学图像或多聚焦图像的融合性能,结合shearlet变换能够捕捉图像细节信息的性质,提出了一种基于shearlet变换的图像融合算法。首先,用shearlet变换将已精确配准的两幅原始图像分解,得到低频子带系数和不同尺度不同方向的高频子带系数。低频子带系数使用改进的加权融合算法,用平均梯度来计算加权参量,以此来改善融合图像轮廓模糊度高的问题,高频子带系数采用区域方差和区域能量相结合的融合规则,以得到丰富的细节信息。最后,进行shearlet逆变换得到融合图像。结果表明,此算法在主观视觉效果和客观评价指标上优于其它融合算法。Abstract: In order to improve the performance of multi-modality medical image fusion and multi-focus image fusion, since the shearlet transform can capture the detail information of images, an image fusion algorithm based on shearlet transform was proposed. Firstly, the shearlet transform was used to decompose the two registered original images, thus the low frequency sub-band coefficients and high frequency sub-band coefficients of different scales and directions were obtained. The fusion principle of low frequency sub-band coefficients was based on the method of weighted fusion, using the average gradient to calculate the weighted parameters in order to improve the edge fuzzy of the fused image. As for the high frequency sub-band coefficients, a fusion rule adopting the region variance combining with the region energy to get the detail information was presented. Finally, the fused image was reconstructed by inverse shearlet transform. The results show that the algorithm is superior to other fusion algorithms on subjective visual effect and objective evaluation.
-
Keywords:
- image processing /
- image fusion /
- shearlet transform /
- weighted fusion /
- region variance /
- region energy
-
-
[1] GAO Y, WANG A M, WANG F H, et al. Application of improved wavelet transform algorithm in image fusion[J]. Laser Technology, 2013, 37(5): 690-695(in Chinese).
[2] YU W J, GU G H, YANG W. Fusion algorithm of infrared polarization images based on wavelet transform[J]. Laser Technology, 2013, 37(3): 289-292(in Chinese).
[3] MINH N D, VETTERLI M. The contourlet transform: an efficient directional multiresolution image representation [J]. IEEE Transactions on Image Processing, 2005, 14(12):2091-2106.
[4] ZHANG Q, GUO B L. Multifocus image fusion using the nonsubsampled contourlet transform[J]. Signal Processing, 2009, 89(7): 1334-1346.
[5] JIAO L C, TAN S. Development and prospect of image multiscale geometric analysis [J]. Acta Electronica Sinica, 2003, 31(12A):1975-1981(in Chinese).
[6] EASLEY G R, LABATE D, LIM W Q. Optimally sparse image representations using shearlets[C]// Fortieth Asilomar Conference on Signals, Systems and Computers. New York, USA:IEEE, 2006: 974-978.
[7] EASLEY G R, LABATE D, LIM W Q. Sparse directional image representations using the discrete shearlet transform[J]. Applied and Computational Harmonic Analysis, 2008, 25(1):25-46.
[8] BORGI M A, LABATE D, EL'ARBI M, et al. Shearlet network-based sparse coding augmented by facial texture features for face recognition[C]//The 17th International Conference on Image Analysis and Processing. Berlin,Germany:Springer, 2013:611-620.
[9] YI S, LABATE D, EASLEY G R. et al. A shearlet approach to edge analysis and detection[J]. IEEE Transactions on Image Processing, 2009, 18(5): 929-941.
[10] HU H Z, SUN H, DENG C Z. Shearlet shrinkage de-noising based total variation regularization [J]. Journal of Image and Graphics, 2011, 16(2):168- 173(in Chinese).
[11] CAO Y, LI S T, HU J W. Multi-focus image fusion by nonsubsampled shearlet transform[C]// 2011 Sixth International Conference on Image and Graphics (ICIG).New York, USA:IEEE, 2011:17-21.
[12] MIAO Q, SHI C, XU P, et al. Multi-focus image fusion algorithm based on shearlets[J]. Chinese Optics Letters, 2011, 9(4): 041001.
[13] MIAO Q, SHI C, XU P, et al. A novel algorithm of image fusion using shearlets[J]. Optics Communications, 2011, 284(6): 1540-1547.
[14] SHI Z, ZHANG Z, YUE Y G. Adaptive image fusion algorithm based on shearlet transform [J]. Acta Photonica Sinica, 2013, 42(1):115-120(in Chinese).
[15] HONG R C. Research on multi-source image fusion and its applications [D].Hefei:University of Science and Technology of China, 2007: 82-88(in Chinese).
[16] HU L M, ZHANG J, XIE Z, et al. Contrast measure based image fusion algorithm in the DCT domain [J]. Chinese Journal of Scientific Instrument, 2007, 28(s3):105-109(in Chinese).
-
期刊类型引用(15)
1. 郑伟，李涵，安晓林，刘帅奇，张晓丹，马泽鹏. 基于ShearLab 3D变换的3维PET/MRI图像融合. 激光技术. 2021(01): 86-92 . 
本站查看
2. 王聪毅，高向东，马女杰，张艳喜，游德勇. 激光焊接缺陷多向磁场激励下磁光成像检测. 激光技术. 2020(05): 592-599 . 本站查看
3. 马女杰，高向东，周晓虎，张艳喜. 磁场激励下焊接缺陷磁光成像特征分析. 激光技术. 2018(04): 525-530 . 本站查看
4. 王烈，罗文，陈俊鸿，秦伟萌. 自适应PCNN与信息提取的红外与可见光图像融合. 计算机工程与应用. 2018(04): 192-198 . 百度学术
5. 王威，张佳娥. 基于引导滤波和shearlet稀疏的遥感图像融合算法. 计算机工程与科学. 2018(07): 1250-1255 . 百度学术
6. 王威，张佳娥. 基于引导滤波和shearlet稀疏的遥感图像融合算法. 计算机工程与科学. 2018(08): 1453-1458 . 百度学术
7. 陈清江，张彦博，柴昱洲，魏冰蔗. 结合区域特性的有限离散剪切波图像融合. 计算机工程与科学. 2017(02): 351-358 . 百度学术
8. 赵学军，刘静. 基于Shearlet和稀疏表示的遥感图像融合. 科学技术与工程. 2017(04): 255-259 . 百度学术
9. 李艳玮，郑伟勇. 改进对比度和空间频率的图像融合算法. 计算机工程与设计. 2017(09): 2457-2463 . 百度学术
10. 葛雯，姬鹏冲，赵天臣. NSST域模糊逻辑的红外与可见光图像融合. 激光技术. 2016(06): 892-896 . 本站查看
11. 周岩，周苑，王旭辉. 基于有限离散剪切波变换的灰度图像融合. 计算机工程. 2016(12): 222-227 . 百度学术
12. 杨丹，何建农. 一种新的结合NSCT和PCNN的图像融合方法. 微型机与应用. 2016(23): 46-48+55 . 百度学术
13. 李慎，王玉德，李妍，王顺. 加权灰度-梯度共生矩阵特征值的图像检索. 电子技术. 2015(12): 7-9 . 百度学术
14. 熊朝松. 大功率LED宽幅数码图像冲印的优化与仿真. 计算机仿真. 2015(08): 276-279+310 . 百度学术
15. 李隆，傅依柳，柴昱洲，陈霄鹏，高当丽，屈子杰. 基于非抽样剪切波的加权区域图像融合. 应用光学. 2015(05): 735-741 . 百度学术
其他类型引用(14)
计量
- 文章访问数: 3
- HTML全文浏览量: 0
- PDF下载量: 11
- 被引次数: 29
下载: