基于方向滤波器组与Laplacian能量和的图像融合算法
|
摘要
目的针对基于Contourlet变换的融合算法在边缘上易出现吉布斯现象,使其融合图像产生几何失真的问题,设计一种非下采样方向滤波器组耦合局部Laplacian能量和的图像融合算法。方法首先,结合多小波变换(multi-wavelet transform,MWT)与非下采样方向滤波器组(Non-Subsampled Direction FilterBank,NSDFB),将图像分解为3个高频方向系数和1个低频系数。对于低频系数,采用局部修正的Laplacian能量和(Local Sum-Modified-Laplacian,LSML)与脉冲耦合神经网络(Pulse couple neural network,PCNN)组合的LSML-PCNN模型来完成低频信息的融合。对于高频系数,通过提取低频和高频子带边缘,并利用系数绝对最大值法作为依据,实现高频系数的融合。结果实验数据表明,与当前图像融合方案相比,所提算法具有更高的融合质量,得到的融合图像边缘更加清晰和完整。结论所提算法拥有较高的融合视觉效果,可改善图像的对比度和分辨率,在图像处理领域具有一定的参考价值。
The work aims to propose an image fusion algorithm based on Non-Subsampled Direction Filter Bank(NSDFB) coupling local Laplacian energy sum, regarding the fusion algorithm based on the Contourlet transform that easily leads to the Gibbs phenomenon on the edge. Firstly, combined with multi-wavelet transform(MWT) and NSDFB, the image was decomposed into three high frequency directional coefficients and one low frequency coefficient. Then, for low frequency coefficient, the LSML-PCNN model composed of Local Sum-Modified-Laplacian(LSML) and pulse couple neural network(PCNN) was used to fuse the low frequency information. For the high frequency coefficient, the low frequency and high frequency subband edges were extracted, and the absolute maximum value method of coefficient was used as the basis to achieve the fusion of high frequency coefficients. The experimental results showed that, the proposed algorithm had higher fusion quality and clearer and more complete edges of the fusion image than the current image fusion scheme. The proposed algorithm has a higher fusion visual effect and it can improve the contrast and resolution of images, which has certain reference value in the field of image processing.
The work aims to propose an image fusion algorithm based on Non-Subsampled Direction Filter Bank(NSDFB) coupling local Laplacian energy sum, regarding the fusion algorithm based on the Contourlet transform that easily leads to the Gibbs phenomenon on the edge. Firstly, combined with multi-wavelet transform(MWT) and NSDFB, the image was decomposed into three high frequency directional coefficients and one low frequency coefficient. Then, for low frequency coefficient, the LSML-PCNN model composed of Local Sum-Modified-Laplacian(LSML) and pulse couple neural network(PCNN) was used to fuse the low frequency information. For the high frequency coefficient, the low frequency and high frequency subband edges were extracted, and the absolute maximum value method of coefficient was used as the basis to achieve the fusion of high frequency coefficients. The experimental results showed that, the proposed algorithm had higher fusion quality and clearer and more complete edges of the fusion image than the current image fusion scheme. The proposed algorithm has a higher fusion visual effect and it can improve the contrast and resolution of images, which has certain reference value in the field of image processing.
引文
[1]叶明,唐敦兵.区域清晰度的小波变换图像融合算法研究[J].电子测量与仪器学报,2015,29(9):1328-1333.YE Ming,TANG Dun-bing.Image Fusion Algorithm Based on Wavelet Transform and Region Image Definition[J].Journal of Electronic Measurement and Instrument,2015,29(9):1328-1333.
[2]陈书贞,任占广,练秋生.基于改进暗通道和导向滤波的单幅图像去雾算法[J].自动化学报,2016,42(3):455-465.CHEN Shu-zhen,REN Zhan-guang LIAN Qiu-sheng.Single Image Dehazing Algorithm Based on Improved Dark Channel Prior and Guided Filter[J].Acta Automatic Sinica,2016,42(3):455-465.
[3]张晓琪,侯世英.基于导向滤波与分形维度的图像加权融合算法[J].包装工程,2018,39(9):220-227.ZHANG Xiao-qi,HOU Shi-ying.Weighted Image Fusion Algorithm Based on Guided Filtering Coupled Fractal Dimension[J].Packaging Engineering,2018,39(9):220-227.
[4]宋瑞霞,王孟,王小春.V-变换和Contourlet变换相结合的图像融合算法[J].计算机工程,2017,43(4):263-268.SONG Rui-xia,WANG Meng,WANG Xiao-chun.Image Fusion Algorithm Combining V-ransform with Contourlet Transform[J].Computer Engineering,2017,43(4):263-268.
[5]XIA Kai-jian,YIN Hong-sheng,WANG Jiang-qiang.ANovel Improved Deep Convolutional Neural Network Model for Image Fusion[J].Cluster Computing,2018(3):1-13
[6]PERYAVATTAM S G,BHUVANESH K.Multimodal Medical Image Fusion in Non-Subsampled Contourlet Transform Domain[J].Circuits and Systems,2016,8(7):1598-1610.
[7]茹庆云,郭献洲.基于图像处理的多小波变化理论及其应用[J].现代电子技术,2017,40(18):95-97.RU Qing-yun,GUO Xian-zhou.Multi-Wavelet Transforms Theory Based on Image Processing and Its Application[J].Modern Electronic Technology,2017,40(18):95-97.
[8]张弢,康缘,任帅.基于压缩感知和GHM多小波变换的信息隐藏算法[J].计算机应用,2017,37(9):2581-2584.ZHANG Tao,KANG Yuan,REN Shuai.Information Hiding Algorithm Based on Compressed Sensing and GHM Multiwavelet transform[J].Computer application,2017,37(9):2581-2584.
[9]王依人,邓国庆,夏营威.基于方向可调滤波器的血管图像增强算法[J].系统仿真学报,2018,30(6):2095-2101.WANG Yi-ren,DENG Guo-qing,XIA Ying-wei.ABlood Vessel Image Enhancement Algorithm Based on Directional Tunable Filter[J].Journal of System Simulation,2018,30(6):2095-2101.
[10]YU Z,YAN L,HAN N.Image Fusion Algorithm Based on Contourlet Transform and PCNN for Detecting Obstacles in Forests[J].Cybern Inf Technol,2015,15(1):116-125.
[11]甘玲,张倩雯.结合NSCT与引导滤波的图像融合方法[J].红外技术,2018,40(5):444-448.GAN Ling,ZHANG Qian-wen.Image Fusion Method Combined with NSCT and Boot Filter[J].Infrared Technology,2018,40(5):444-448.
[12]任晓霞,孙秀明,耿鹏.多小波和NSDFB组合域递归滤波多聚焦图像融合[J].智能系统学报,2016,11(2):241-248.REN Xiao-xia,SUN Xiu-ming,GENG Peng.Multi Focus and Image Fusion Based on Recursive Filtering of Multiwavelet and NSDFB Combination Domain[J].Journal of Intelligent System,2016,11(2):241-248.
[13]LIU Shuai-qi,ZHAO Jie,SHI Ming-zhu.Medical Image Fusion Based on Improved Sum-ModifiedLaplacian[J].International Journal of Imaging Systems and Technology,2015,25(3):206-212
[14]XU Xin-zheng,WANG Guan-ying,DING Shi-fei.Pulse-Coupled Neural Networks and Parameter Optimization Methods[J].Neural Computing and Applications,2017,28(1):671-681.
[15]SONG Ren-jie,ZHANG Zi-qi,LIU Hai-yang.Edge Connection Based Canny Edge Detection Algorithm[J].Pattern Recognition and Image Analysis,2017,27(4):740-747.
[16]杨建平,帅晓勇,陶黄林.被淹没地震信号的小波熵检测与自动识别方法[J].井冈山大学学报(自然科学版),2015,36(4):43-48.YANG Jian-ping,SHUAI Xiao-yong,TAO Huang-lin.Wavelet Entropy Detection and Automatic Recognition of Submerged Seismic Signals[J].Journal of Jinggangshan University,2015,36(4):43-48.
[17]WEI Chun-yu,ZHOU Bing-yin,GUO Wei.Multi-Focus Image Fusion Based on Nonsubsampled Compactly Supported Shearlet Transform[J].Multimedia Tools and Applications,2018,77(7):8327-8358.
[18]岳静静,李茂忠,陈骥.基于NSCT-PCNN的多聚焦红外图像融合[J].红外技术,2017,39(9):798-806.YUE Jing-jing,LI Mao-zhong,CHEN Ji.Multi-Focus Infrared Image Fusion Based on Pulse Coupled Neural Networks in a Nonsubsampled Contourlet Transform Domain[J].Infrared Technology,2017,39(9):798-806.
[19]赵岩,孟丽茹,王世刚.符合人眼视觉感知特性的改进PSNR评价方法[J].吉林大学学报(工学版),2015,45(1):309-313.ZHAO Yan,MENG Li-ru,WANG Shi-gang.Improved PSNR Evaluation Method Consistent with Human Visual Perception[J].Journal of Jilin University(Engineering and Technology Edition),2015,45(1):309-313.
[2]陈书贞,任占广,练秋生.基于改进暗通道和导向滤波的单幅图像去雾算法[J].自动化学报,2016,42(3):455-465.CHEN Shu-zhen,REN Zhan-guang LIAN Qiu-sheng.Single Image Dehazing Algorithm Based on Improved Dark Channel Prior and Guided Filter[J].Acta Automatic Sinica,2016,42(3):455-465.
[3]张晓琪,侯世英.基于导向滤波与分形维度的图像加权融合算法[J].包装工程,2018,39(9):220-227.ZHANG Xiao-qi,HOU Shi-ying.Weighted Image Fusion Algorithm Based on Guided Filtering Coupled Fractal Dimension[J].Packaging Engineering,2018,39(9):220-227.
[4]宋瑞霞,王孟,王小春.V-变换和Contourlet变换相结合的图像融合算法[J].计算机工程,2017,43(4):263-268.SONG Rui-xia,WANG Meng,WANG Xiao-chun.Image Fusion Algorithm Combining V-ransform with Contourlet Transform[J].Computer Engineering,2017,43(4):263-268.
[5]XIA Kai-jian,YIN Hong-sheng,WANG Jiang-qiang.ANovel Improved Deep Convolutional Neural Network Model for Image Fusion[J].Cluster Computing,2018(3):1-13
[6]PERYAVATTAM S G,BHUVANESH K.Multimodal Medical Image Fusion in Non-Subsampled Contourlet Transform Domain[J].Circuits and Systems,2016,8(7):1598-1610.
[7]茹庆云,郭献洲.基于图像处理的多小波变化理论及其应用[J].现代电子技术,2017,40(18):95-97.RU Qing-yun,GUO Xian-zhou.Multi-Wavelet Transforms Theory Based on Image Processing and Its Application[J].Modern Electronic Technology,2017,40(18):95-97.
[8]张弢,康缘,任帅.基于压缩感知和GHM多小波变换的信息隐藏算法[J].计算机应用,2017,37(9):2581-2584.ZHANG Tao,KANG Yuan,REN Shuai.Information Hiding Algorithm Based on Compressed Sensing and GHM Multiwavelet transform[J].Computer application,2017,37(9):2581-2584.
[9]王依人,邓国庆,夏营威.基于方向可调滤波器的血管图像增强算法[J].系统仿真学报,2018,30(6):2095-2101.WANG Yi-ren,DENG Guo-qing,XIA Ying-wei.ABlood Vessel Image Enhancement Algorithm Based on Directional Tunable Filter[J].Journal of System Simulation,2018,30(6):2095-2101.
[10]YU Z,YAN L,HAN N.Image Fusion Algorithm Based on Contourlet Transform and PCNN for Detecting Obstacles in Forests[J].Cybern Inf Technol,2015,15(1):116-125.
[11]甘玲,张倩雯.结合NSCT与引导滤波的图像融合方法[J].红外技术,2018,40(5):444-448.GAN Ling,ZHANG Qian-wen.Image Fusion Method Combined with NSCT and Boot Filter[J].Infrared Technology,2018,40(5):444-448.
[12]任晓霞,孙秀明,耿鹏.多小波和NSDFB组合域递归滤波多聚焦图像融合[J].智能系统学报,2016,11(2):241-248.REN Xiao-xia,SUN Xiu-ming,GENG Peng.Multi Focus and Image Fusion Based on Recursive Filtering of Multiwavelet and NSDFB Combination Domain[J].Journal of Intelligent System,2016,11(2):241-248.
[13]LIU Shuai-qi,ZHAO Jie,SHI Ming-zhu.Medical Image Fusion Based on Improved Sum-ModifiedLaplacian[J].International Journal of Imaging Systems and Technology,2015,25(3):206-212
[14]XU Xin-zheng,WANG Guan-ying,DING Shi-fei.Pulse-Coupled Neural Networks and Parameter Optimization Methods[J].Neural Computing and Applications,2017,28(1):671-681.
[15]SONG Ren-jie,ZHANG Zi-qi,LIU Hai-yang.Edge Connection Based Canny Edge Detection Algorithm[J].Pattern Recognition and Image Analysis,2017,27(4):740-747.
[16]杨建平,帅晓勇,陶黄林.被淹没地震信号的小波熵检测与自动识别方法[J].井冈山大学学报(自然科学版),2015,36(4):43-48.YANG Jian-ping,SHUAI Xiao-yong,TAO Huang-lin.Wavelet Entropy Detection and Automatic Recognition of Submerged Seismic Signals[J].Journal of Jinggangshan University,2015,36(4):43-48.
[17]WEI Chun-yu,ZHOU Bing-yin,GUO Wei.Multi-Focus Image Fusion Based on Nonsubsampled Compactly Supported Shearlet Transform[J].Multimedia Tools and Applications,2018,77(7):8327-8358.
[18]岳静静,李茂忠,陈骥.基于NSCT-PCNN的多聚焦红外图像融合[J].红外技术,2017,39(9):798-806.YUE Jing-jing,LI Mao-zhong,CHEN Ji.Multi-Focus Infrared Image Fusion Based on Pulse Coupled Neural Networks in a Nonsubsampled Contourlet Transform Domain[J].Infrared Technology,2017,39(9):798-806.
[19]赵岩,孟丽茹,王世刚.符合人眼视觉感知特性的改进PSNR评价方法[J].吉林大学学报(工学版),2015,45(1):309-313.ZHAO Yan,MENG Li-ru,WANG Shi-gang.Improved PSNR Evaluation Method Consistent with Human Visual Perception[J].Journal of Jilin University(Engineering and Technology Edition),2015,45(1):309-313.