CAJ | 학술논문

针对小波变换与Contourlet变换的不足，提出了一种将非下采样Contourlet 变换与主成分分析相结合的图像融合算法。对已配准好的融合源图像作NSCT分解，采用PCA加权融合规则对低频系数处理，采用边缘强度最大的规则对各高频子带系数作融合处理，分别得到融合图像的变换系数，对该系数经NSCT逆变换重构得到融合图像。实验结果表明，算法有效地融合了源图像中的重要信息，融合图像边缘、纹理、细节清晰，得到较好视觉效果和较优的评价指标。
침대소파변환여Contourlet변환적불족，제출료일충장비하채양Contourlet 변환여주성분분석상결합적도상융합산법。대이배준호적융합원도상작NSCT분해，채용PCA가권융합규칙대저빈계수처리，채용변연강도최대적규칙대각고빈자대계수작융합처리，분별득도융합도상적변환계수，대해계수경NSCT역변환중구득도융합도상。실험결과표명，산법유효지융합료원도상중적중요신식，융합도상변연、문리、세절청석，득도교호시각효과화교우적평개지표。
In this paper , a novel algorithm is proposed combining Nonsubsampled Contourlet Transform and Principal Component Analysis to avoid the disadvantages of Wavelet transform and Contourlet trans -form.The registered images are decomposed by NSCT .We can obtain the low-frequency subimages and a series high-frequency subimages .The weighted PCA is applied to the low-frequency subimages .And the rule of edge intensity is applied to the high-frequency subimages .Then the fusion image is obtained by inverse NSCT .Experimental results show that the proposed method can retain a visual quality and objec -tive evaluation index ,and performs some related fusion approaches .