基于Shearlet域的改进加权法结合自适应PCNN的图像融合算法

doi:10.11896/j.issn.1002-137X.2019.04.041

摘要/Abstract

摘要： 针对传统多聚焦图像融合算法获得的融合图像对比度低的问题,提出基于改进加权法和自适应脉冲耦合神经网络的多聚焦图像融合算法。首先,源图像经Shearlet分解产生一个低频子带和一系列不同尺度、不同方向的高频子带。将源图像的低频子带的和以及低频子带的差的绝对值进行加权求和,采用平均梯度计算权值,得到融合后的低频子带;高频子带采用自适应脉冲耦合神经网络融合规则,其中,脉冲耦合神经网络采用改进的拉普拉斯能量和作为激励,其链接强度由源图像的区域空间频率自适应计算,根据脉冲耦合神经网络的点火映射图得到融合后的高频子带,最后经Shearlet逆变换得到融合图像。文中选择1组人工仿真多聚焦图像Cameraman和3组真实的多聚焦图像Pepsi,Clock和Peppers进行实验,并与其他7种融合方法进行比较,采用4种常见的质量评价指标对融合图像进行客观评价。实验结果表明,所提方法在主观视觉和客观评价上均有较好的效果。

关键词: Shearlet变换, 多聚焦图像融合, 空间频率, 脉冲耦合神经网络, 平均梯度

Abstract: Since traditional multi-focus image fusion algorithm has the problem of low contrast ratio,this paper presented a multi-focus image fusion algorithm based on improved weighted method and adaptive pulse coupled neural network (PCNN) in Shearlet domain.Firstly,the source images are decomposed by Shearlet transform to generate a low-frequency subband and a series of high-frequency subbands with different scales in different directions,then the weighted sum of the low-frequency subbands and the absolute value of the difference of the low-frequency subbands are conducted,the weight is calculated by the average gradient,and finally the fused low-frequency subbands are obtained.At the same time,the high-frequency subbands are fused by adaptive PCNN fusion rule,the motivation for PCNN is calculated by sum-modified Laplacian,the linking strength for PCNN is adaptively calculated by the regional spatial frequency of each source images,and the fused high-frequency subbands are obtained according to the ignition map of PCNN.Finally,the fusion image is acquired by the Shearlet inverse transform.One group of artificial simulated multi-focus images named Cameraman and three groups of real multi-focus images named Pepsi,Clock and Peppers are selected respectively for experiments,seven different fusion methods are chosen as a comparison,and four common quality evaluation indexes are used to evaluate the fusion images objectively.The experimental results show that the proposed method has good performance both on subjective vision and objective evaluation.

Key words: Average gradient, Multi-focus image fusion, Pulse coupled neural network, Shearlet transform, Spatial frequency

中图分类号:

TP751

王英, 刘帆, 陈泽华. 基于Shearlet域的改进加权法结合自适应PCNN的图像融合算法[J]. 计算机科学, 2019, 46(4): 261-267. https://doi.org/10.11896/j.issn.1002-137X.2019.04.041

WANG Ying, LIU Fan, CHEN Ze-hua. Image Fusion Algorithm Based on Improved Weighted Method and AdaptivePulse Coupled Neural Network in Shearlet Domain[J]. Computer Science, 2019, 46(4): 261-267. https://doi.org/10.11896/j.issn.1002-137X.2019.04.041

参考文献

[1]WANG J H,WANG W Q,LI B,et al.Exposure fusion via sparse representation and shiftable complex directional pyramid transform[J].Multimedia Tools & Applications,2016,76(14):1-21.
[2]CAI M,YANG Y,CAI G.Multi-focus image fusion algorithm using LP transformation and PCNN[C]∥IEEE International Conference on Software Engineering and Service Science.IEEE,2015:237-241.
[3]VANI M,SARAVANAKUMAR S.Multi focus and multi modal image fusion using wavelet transform[C]∥International Conference on Signal Processing,Communication and Networking.IEEE,2015:1-6.
[4]SONAM,KUMAR M.Discrete Wavelet Transform and Cross Bilateral Filter based Image Fusion[J].International Journal of Intelligent Systems & Applications,2017,9(1):37-45.
[5]TAI J H,PAN B,ZHAO S S,et al.SAR and Multispectral Remote Sensing Image Fusion Method Using Shearlet Transform[J].Geomatics and Information Science of Wuhan University,2017,42(4):468-474.(in Chinese) 邰建豪,潘斌,赵珊珊,等.基于Shearlet变换的SAR与多光谱遥感影像融合[J].武汉大学学报(信息科学版),2017,42(4):468-474.
[6]YIN M,DUAN P H,LIU W,et al.A novel infrared and visible image fusion algorithm based on shift-invariant dual-tree complex shearlet transform and sparse representation[J].Neurocomputing,2016,226(C):182-191.
[7]焦李成,侯彪,王爽,等.图像多尺度几何分析理论与应用[M].西安:西安电子科技大学出版社,2008:485-497.
[8]马义德,李廉,绽琨,等.脉冲耦合神经网络与数字图像处理[M].北京:科学出版社,2008:16-28.
[9]PENG G,WANG Z Y,ZHANG Z G,et al.Image fusion by pulse couple neural network with shearlet[J].Optical Enginee-ring,2012,51(6):1-7.
[10]LIAO Y,HUANG W L,SHANG L,et al.Image fusion based on Shearlet and improved PCNN[J].Computer Engineering and Applications,2014,50(2):142-146.(in Chinese) 廖勇,黄文龙,尚琳,等.Shearlet与改进PCNN相结合的图像融合[J].计算机工程与应用,2014,50(2):142-146.
[11]WANG Y J,PAN Q B,WU Y Y,et al.A fusion method for visible light and infrared images based on FFST and compressed sensing[C]∥Control and Decision Conference.IEEE,2017.
[12]MIAO Q G,SHI C,XU P F,et al.A novel algorithm of image fusion using shearlets[J].Optics Communications,2011,284(6):1540-1547.
[13]MIAO Q G,SHI C,XU P F,et al.Multi-focus image fusion algorithm based on shearlets[J].Chinese Optics Letters,2011,9(4):25-29.
[14]WANG Z B,WANG S,ZHU Y.Multi-focus Image Fusion Based on the Improved PCNN and Guided Filter[J].Neural Processing Letters,2017,45(1):75-94.
[15]马义德.脉冲耦合神经网络原理及其应用[M].北京:科学出版社,2006:16-20.
[16]ZHU F Z,JIANG A P,ZHU B,et al.Multifocus image fusion based on Uniform Discrete Curvelet Transform[C]∥International Conference on Estimation,Detection and Information Fusion.IEEE,2015:129-134.
[17]SHI Z,ZHANG Z,YUE Y G.Adaptive Image Fusion Algorithm Based on Shearlet Transform[J].Photonics,2013,42(1):115-120.(in Chinese) 石智,张卓,岳彦刚.基于Shearlet变换的自适应图像融合算法[J].光子学报,2013,42(1):115-120.
[18]HUANG W,JING Z L.Evaluation of focus measures in multi-focus image fusion[J].Pattern Recognition Letters,2007,28(4):493-500.
[19]MA Y D,DAI R L,LI L.An Automatic Image Segmentation Method Based on Pulse Coupled Neural Network and Image Entropy[J].Journal of Communications,2002,23(1):46-51.(in Chinese) 马义德,戴若兰,李廉.一种基于脉冲耦合神经网络和图像熵的自动图像分割方法[J].通信学报,2002,23(1):46-51.
[20]XYDEAS C S,PETROVIC V.Objective image fusion performance measure[J].Military Technical Courier,2000,56(2):181-193.
[21]QU G H,ZHANG D L,YAN P F.Information measure for performance of image fusion[J].Electronics Letters,2002,38(7):313-315.
[22]WANG Z H,WANG J Q,ZHAO D G,et al.Image fusion based on Shearlet and improved PCNN [J].Laser & Infrared,2012,42(2):213-216.(in Chinese) 王朝晖,王佳琪,赵德功,等.基于Shearlet与改进PCNN的图像融合[J].激光与红外,2012,42(2):213-216.
[23]YANG Y,WAN W G,HUANG S Y,et al.Sparse Representation and Non-subsampled Shearlet Transform for Multi-focus Image Fusion[J].Journal of Chinese Computer Systems,2017,38(2):386-392.(in Chinese) 杨勇,万伟国,黄淑英,等.稀疏表示和非下采样Shearlet变换相结合的多聚焦图像融合[J].小型微型计算机系统,2017,38(2):386-392.
[24]WANG H M,QI Z L.A novel image fusion algorithm using adaptive PCNN based on artificial fish swarm optimization [J].Journal of Optoelectronics·Laser,2017,28(4):427-432.(in Chinese) 王红梅,亓子龙.基于人工鱼群优化的自适应脉冲耦合神经网络图像融合[J].光电子·激光,2017,28(4):427-432.

相关文章 15

[1]	黄晓生, 徐静. 基于PCANet的非下采样剪切波域多聚焦图像融合 Multi-focus Image Fusion Method Based on PCANet in NSST Domain 计算机科学, 2021, 48(9): 181-186. https://doi.org/10.11896/jsjkx.200800064
[2]	温荷, 罗频捷. 基于改进脉冲耦合神经网络的动态人脸识别 Dynamic Face Recognition Based on Improved Pulse Coupled Neural Network 计算机科学, 2021, 48(6A): 85-88. https://doi.org/10.11896/jsjkx.200600172
[3]	李昌兴, 雷柳, 张晓璐. 基于形态学图像增强和PCNN的脑部CT与MRI图像融合 Brain CT and MRI Image Fusion Based on Morphological Image Enhancement and PCNN 计算机科学, 2020, 47(10): 194-199. https://doi.org/10.11896/jsjkx.190700185
[4]	张冰, 谢从华, 刘哲. 基于显著稀疏表示和邻域信息的多聚焦图像融合 Multi-focus Image Fusion Based on Latent Sparse Representation and Neighborhood Information 计算机科学, 2019, 46(9): 254-258. https://doi.org/10.11896/j.issn.1002-137X.2019.09.038
[5]	曹义亲, 曹婷, 黄晓生. 基于àtrous-NSCT变换和区域特性的图像融合方法 Image Fusion Method Based on àtrous-NSCT Transform and Region Characteristic 计算机科学, 2019, 46(6): 270-276. https://doi.org/10.11896/j.issn.1002-137X.2019.06.040
[6]	孙艺彬, 杨慧珍. 基于定向约束的脉冲耦合神经网络路径规划 Path Planning Based on Pulse Coupled Neural Networks with Directed Constraint 计算机科学, 2019, 46(11A): 28-32.
[7]	毛义坪, 余磊, 官泽瑾. 基于分数阶微分的多聚焦图像融合 Multi-focus Image Fusion Based on Fractional Differential 计算机科学, 2019, 46(11A): 315-319.
[8]	王燕,许宪法. 基于显著性与脉冲耦合神经网络的图像分割 Image Segmentation Based on Saliency and Pulse Coupled Neural Network 计算机科学, 2018, 45(7): 259-263. https://doi.org/10.11896／j.issn.1002-137X.2018.07.045
[9]	侯瑞超,周冬明,聂仁灿,刘栋,郭晓鹏. 结合视觉显著性与Dual-PCNN的红外与可见光图像融合 Infrared and Visible Images Fusion Using Visual Saliency and Dual-PCNN 计算机科学, 2018, 45(6A): 162-166.
[10]	杨艳春,李娇,党建武,王阳萍. 基于冗余小波变换与引导滤波的多聚焦图像融合 Multi-focus Image Fusion Based on Redundant Wavelet Transform and Guided Filtering 计算机科学, 2018, 45(2): 301-305. https://doi.org/10.11896/j.issn.1002-137X.2018.02.052
[11]	杨利素, 王雷, 郭全. 基于NSST与自适应PCNN的多聚焦图像融合方法 Multi-focus Image Fusion Method Based on NSST and Adaptive PCNN 计算机科学, 2018, 45(12): 217-222. https://doi.org/10.11896／j.issn.1002-137X.2018.12.036
[12]	王爱文,宋玉阶. 基于脉冲耦合神经网络的图像分割 Image Segmentation Based on Pulse Coupled Neural Network 计算机科学, 2017, 44(4): 317-322. https://doi.org/10.11896/j.issn.1002-137X.2017.04.064
[13]	王佺,聂仁灿,金鑫,周冬明,贺康建,余介夫. 基于拉普拉斯金字塔与PCNN-SML的图像融合算法 Image Fusion Algorithm Using LP Transformation and PCNN-SML 计算机科学, 2016, 43(Z6): 122-124. https://doi.org/10.11896/j.issn.1002-137X.2016.6A.029
[14]	曹春红,张建华,李林峰. 基于双子代差分演化和自适应分块机制的多聚焦图像融合算法 Multi-focus Image Fusion Based on Twin-generation Differential Evolution and Adaptive Block Mechanism 计算机科学, 2016, 43(7): 67-72. https://doi.org/10.11896/j.issn.1002-137X.2016.07.011
[15]	寇光杰,马云艳,岳峻,邹海林. 一种基于视皮层神经元模型的彩色图像签名算法 Color Image Signature Algorithm Based on Visual Cortex Neuron Model 计算机科学, 2015, 42(Z11): 189-191.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed