一种基于NSCT和PCNN的图像融合算法  

Image Fusion Algorithm in NSCT Domain Based on PCNN

作　　者：石瀚洋 杨静[1] 赵焱[1] 

机构地区：[1]太原理工大学信息工程学院,山西太原030024

出　　处：《电视技术》2014年第9期247-250,共4页Video Engineering

摘　　要：在NSCT变换域提出了一种基于清晰度和PCNN的图像融合算法。首先对源图像分别进行NSCT变换,得到一组高频子带,和一个低频子带。然后对低频子带用提出的边缘清晰度算法进行融合处理,对高频子带,用提出的空间频率做链接强度的自适应PCNN算法进行融合处理。最后通过NSCT逆变换得到融合结果图像。对融合图像的结果分析证明,该算法在主观评价和客观评价指标方面都有所提高。An image fusion algorithm by combing Nonsubsampled Contourlet Transform （NSCT）and Pulse Coupled Neural Network（PCNN） is presen- ted in this paper. This algorithm could improve the quality of image fusion from improving image definition. Firstly,two primitive matched images are de- composed in NSCT domain. The low frequency used the fusion based on definition. The high frequency coefficients are input to the adaptive PCNN. Final- ly,the fused image is obtained through inverse NSCT. The simulation results show that the results are much better than the experimental results,which the mutual information and definition are higher than the contrast method of fusion results.

关 键 词：非下采样CONTOURLET变换 清晰度 脉冲耦合神经网络 多聚焦图像融合 

分 类 号：TN911.73[电子电信—通信与信息系统] TP317.4[电子电信—信息与通信工程]