基于改进PCNN的压缩感知域图像融合.pdfVIP

第45 卷第11 期 激光与红外 Vol. 45 ,No. 11 2015 年 11 月 LASER INFRARED November ,2015 文章编号:1∞1-5078(2015) 11-1392..QS ·图像与信号处理· 基于改进 PCNN 的压缩感知域图像融合 刘斌，田中佳 (燕山大学电气工程学院，河北秦皇岛 066(阳) 摘 要:提出了一种压缩感知域基于改进 PCNN 的图像融合算法。根据压缩采样得到待融合 图像的压缩观测值，建立改进 PCNN 模型，即利用压缩观测值的物理意义对 PCNN 中连接系 数，加权矩阵和特征参数进行自适应设定。并将压缩观测值作为改进 PCNN 神经元输入获取 点火映射图作为融合算子，对源图像观测值融合后进行重构得到融合图像。实验结果表明，该 算法克服现有压缩感知图像融合算法细节丢失的缺陷，主客观评价优于现有压缩感知图像融 合算法。 关键词:图像融合;压缩观测值;脉冲糯合神经网络;自适应调节 中图分类号:TP391. 41 文献标识码:A DOI: 1O.3969/j.issn. 1001-5078.2015. 1 1. 021 Image fusion algorithm based on improved PCNN in compressed sensing domain LIU Bin ，咀AN Zhong-jia (School of Electrical Engineeri吨，Yanshan University ,Qinhuangdao 066∞4 ， China) Abstract: An image fusion algorithm based on improved PCNN is proposed in compressive sensing domain. Original images are compressed by compressed sensing to obtain measurements. Improved PCNN model is built based on physi- cal significance of measurements. Namely link coefficient ,weighting matrix and threshold amplification coefficient are set adaptively. Measurements are selected as input neuron to obtain ignition-map as fusion operator. Fusion image is obtained according to reconstructing algorithm. The results show that this algorithm overcomes the detail missing of tra- ditional compressed sensing image fusion ,and the subjective and objective evaluation indexes show that this method is superior to the existing compressed sensing image fusion methods. Key words: