摘要
针对医学图像融合过程中出现的细节损失严重、视觉效果不佳问题,提出了一种基于非下采样轮廓波变换(NSCT)与离散小波变换(DWT)的脉冲耦合神经网络(PCNN)医学图像融合算法。首先,利用NSCT处理医学源图像,得到相应的低频和高频子带,并利用DWT对得到的低频子带进行处理。然后,利用PCNN对低频子带进行融合,将平均梯度和改进型拉普拉斯能量和作为PCNN的输入项,将信息熵与匹配度结合实现对高频子的融合。最后,利用多尺度逆变换将低频子带和高频子带图像进行融合。实验结果表明,所提方法能够有效提升融合图像的对比度并保留源图像的细节信息,在主观和客观评价上均有优良的性能表现。
Aiming at the serious loss of details and poor visual effect in the process of medical image fusion,apulse coupled neural network(PCNN)medical image fusion algorithm based on non-subsampled contourlet transform(NSCT)and discrete wavelet transform(DWT)is proposed.Firstly,the medical source image is processed by NSCT to obtain the corresponding low frequency and high frequency subbands,and the obtained low frequency subbands are processed by DWT.Then,the PCNN is used to fuse the low frequency subbands,where the input items are the average gradient and the improved Laplacian energy sum.The fusion of high frequency subbands is realized by combining information entropy and matching degree.Finally,the low frequency subband image and high frequency subband image are fused by multi-scale inverse transformation.Experimental results show that the proposed method can effectively improve the contrast of the fused image and retain the detailed information of the source image,and has excellent performance in both subjective and objective evaluation.
作者
赵贺
张金秀
张正刚
Zhao He;Zhang Jinxiu;Zhang Zhenggang(School of Electronic and Information Engineering,Lanzhou Jiaotong University,Lanzhou,Gansu 730070,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2021年第20期445-454,共10页
Laser & Optoelectronics Progress
关键词
医用光学
图像融合
非下采样轮廓波变换
离散小波变换
脉冲耦合神经网络
medical optics
image fusion
non-subsampled contourlet transform
discrete wavelet transform
pulse coupled neural network
