首页 > 论文 > 光学 精密工程 > 22卷 > 1期(pp:169-176)

基于多尺度稀疏字典的多聚焦图像超分辨融合

Superresolution fusion of multi-focus image based on multiscale sparse dictionary

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

由于传统的多聚焦图像融合算法不能对图像中聚焦区域划分进行有效度量,提出了一种新的多聚焦图像超分辨融合方法来改善图像融合效果。该方法对图像清晰区和模糊区进行度量,并利用稀疏表示方法对度量后的清晰区域进行超分辨重建。首先,采用空间频率方法提取源图像中清晰区域与模糊区域,然后确定清晰区域中的主清晰区和次清晰区,并计算它们的真实下采样尺度。最后,通过学习多尺度稀疏表示字典对图像中次清晰区域进行超分辨率重建,并与清晰区域结合形成最终融合图像。实验及各种定量评价结果表明,提出的方法较常规方法具有更好的融合性能,得到的图像更清晰。对比Harr小波,非下采样轮廓波变换(NSCT),剪切波(Shearlet)变换等方法,其熵(EN)提升了1%,峰值信噪比(PSNR)提升了0.62 dB,清晰度(SP)和空间频率(SF)提升30%,均方误差(MSE)下降了6%左右。

Abstract

As traditional multi-focus image fusion methods can not effectively measure the partitioning focus regions in images, a novel algorithm by using super-resolution image reconstruction for multi-focus image fusion was proposed to solve the problem. The algorithm measured the in-focus and out-of-focus regions and performed the super-resolution image reconstruction for the clear area with sparse representation. Firstly, the spatial frequency method was used to extract the in-focus and out-of-focus regions in source images. Then, the main-clear and sub-clear parts within in-focus regions were identified and their real down-sampling scales for each part were calculated. Finally, the sub-clear parts were reconstructed in super-resolution through learning multi-scale sparse dictionaries and the fused image was obtained by combining the different parts of source images. The experimental results show that the proposed method can provide clear images and better facus performance. As compared with the conventional methods, such as Harr wavelet, Nonsubsampled Contourlet Transform (NSCT), and shearlet transform,the proposed method enhances its Entropy (EN) and Peak Signal-to-Noise Ratio (PSNR) by 1%,and 0.62dB, respectively, the clarity (SP) and spatial frequency (SF) by 30%, and the Mean Square Error (MSE) is decreased by about 6%.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.4

DOI:10.3788/ope.20142201.0169

所属栏目:信息科学

基金项目:国家自然科学基金资助项目(No.41301460;No.61308102); 中国科学院光束控制重点实验室基金资助项目(No.2010LBC001),中央高校基本科研业务费专项资金资助项目(No.ZYGX2010J063)

收稿日期:2013-08-16

修改稿日期:2013-09-11

网络出版日期:--

作者单位    点击查看

彭真明:电子科技大学 光电信息学院,四川 成都 610054
景亮:电子科技大学 光电信息学院,四川 成都 610054
何艳敏:电子科技大学 光电信息学院,四川 成都 610054
张萍:电子科技大学 光电信息学院,四川 成都 610054

联系人作者:彭真明(zmpeng@uestc.edu.cn)

备注:彭真明(1966-),男,湖南保靖人,博士,教授,博士生导师,主要从事图像处理与分析、成像目标检测识别与跟踪、雷达信号及SAR图像处理、地球物理反演与油气储层预测等方面的研究。

【1】苗启广,王宝树. 一种自适应PCNN多聚焦图像融合新方法[J]. 电子与信息学报, 2006, 28(3): 466-470.
MIAO Q G, WANG B SH. A novel algorithm of multi-focus image fusion using adaptive pCNN [J]. Journal Electronics & Information Technology, 2006, 28(3): 466-470.(in Chinese)

【2】HUANG W, JING ZH L. Multi-focus image fusion using pulse coupled neural network [J]. Pattern Recognition Letters, 2007, 28(9): 1123-1132.

【3】TIAN J, CHEN L, MA L H, et al.. Multi-focus image fusion using a bilateral gradient-based sharpness criterion [J]. Optics Communications, 2011, 284(1): 80-87.

【4】张雄美, 李俊山, 易昭湘, 等. 非抽样轮廓波变换域图像融合方法研究[J]. 电光与控制, 2008, 15(7): 16-19.
ZHANG X M, LI J SH, YI ZH X, et al.. Image fusion based on nonsampled contourlet[J]. Electronics Optical & Control, 2008, 15(7): 16-19.(in Chinese)

【5】MIAO Q G, SHI CH, XU P F, et al.. Multi-focus image fusion algorithm based on shearlets [J]. Chinese Optics Letters, 2011,9(4): 1-5.

【6】ESKICIOGLU A M. Image quality measures and their performance [J]. IEEE Transactions on Communications, 1995, 43(12): 2959-2965.

【7】KONG J, ZHENG K Y, ZHANG J B, et al.. Multi-focus image fusion using spatial frequency and genetic algorithm[J]. International Journal of Computer Science and Network Security, 2008, 8(2): 220-224.

【8】LI SH T, YANG B. Multi-focus image fusion using region segmentation and spatial frequency [J]. Image and Vision Computing, 2008, 26(7): 971-979.

【9】MARUTHI R. Multi focus image fusion technique in spatial domain using an image variance as a focus measure [J]. Journal on Future Engineering and Technology, 2010, 5(3): 24-31.

【10】HE Y M, GAN T, CHEN W F, et al.. Multi-stage image denoising based on correlation coefficient matching and sparse dictionary pruning [J]. Signal Processing, 2012, 92: 139-149.

【11】何艳敏, 甘涛, 陈武凡. 基于稀疏表示的两级图像去噪[J]. 电子与信息学报, 2012, 34(9): 2268-2272.
HE Y M, GAN T, CHEN W F. Two-stage Image Denoising Based on Sparse Representations [J]. Journal of Electronics & Information Technology, 2012, 34(9): 2268-2272.(in Chinese)

【12】YANG J CH, JOHN W, HUANG T S, et al.. Image super-resolution via sparse representation[J]. IEEE Transactions on Image Processing, 2010, 19(11): 2861-2873.

【13】ZEYDE R, ELAD M, PROTTER M. On single image scale-up using sparse-representations[J]. Curves and Surfaces, 2010: 711-730.

【14】路锦正, 张启衡, 徐智勇, 等. 光滑逼近超完备稀疏表示的图像超分辨率重构[J]. 光电工程, 2012, 39(2): 123-129.
LU J ZH, ZHANG Q H, XU ZH Y, et al.. Image super-resolution reconstruction based on smoothly approximate over-complete sparse representation [J]. Opto-Electronic Engineering, 2012, 39(2): 123-129.(in Chinese)

【15】路锦正, 张启衡, 徐智勇, 等. 超完备稀疏表示的图像超分辨率重构方法[J]. 系统工程与电子技术, 2012, 34(2): 403-408.
LU J ZH, ZHANG Q H, XU ZH Y, et al.. Image super-resolution reconstruction algorithm using over-complete sparse representation[J]. Systems Engineering and Electronics, 2012, 34(2): 403-408.(in Chinese)

【16】AHARON M, ELAD M, BRUCKSTEIN A M. K-SVD: An algorithm for designing over-complete dictionaries for sparse representation[J]. IEEE Trans. on Signal Processing, 2006, 54(11): 4311-4322.

引用该论文

PENG Zhen-ming,JING Liang,HE Yan-min,Zhang Ping. Superresolution fusion of multi-focus image based on multiscale sparse dictionary[J]. Optics and Precision Engineering, 2014, 22(1): 169-176

彭真明,景亮,何艳敏,张萍. 基于多尺度稀疏字典的多聚焦图像超分辨融合[J]. 光学 精密工程, 2014, 22(1): 169-176

被引情况

【1】李勇,苗壮,王青竹. 纹理引导的稀疏张量表示及在肺CT图像中的应用. 光学 精密工程, 2015, 23(2): 550-556

【2】周琳,杨娜. 基于离线双字典学习算法的图像超分辨率重建研究. 红外技术, 2015, 37(4): 277-282

【3】李宗剑,邹晓兵. 快速Arclet变换及其在工业CT图像圆测量中的应用. 光学 精密工程, 2015, 23(8): 2400-2406

【4】穆绍硕,张叶,贾平. 基于自学习局部线性嵌入的多幅亚像元超分辨成像. 光学 精密工程, 2015, 23(9): 2677-2686

【5】翟海天,李辉,李彬. 基于区域划分的红外超分辨率重建. 光学 精密工程, 2015, 23(10): 2989-2996

【6】张振东,陈健,王伟国,刘廷霞. 基于SSIM_NCCDFT的超分辨率复原评价方法研究. 液晶与显示, 2015, 30(4): 713-721

【7】赵康,吴谨. 一种改进的基于区域梯度——能量的图像融合方法. 液晶与显示, 2016, 31(3): 331-337

【8】殷 明,段普宏,褚 标,梁翔宇. 基于非下采样双树复轮廓波变换和稀疏表示的红外和可见光图像融合. 光学 精密工程, 2016, 24(7): 1763-1771

【9】何 阳,黄 玮,王新华,郝建坤. 稀疏阈值的超分辨率图像重建. 中国光学, 2016, 9(5): 532-539

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF