摘要: 提出一种基于主成分分析(PCA)分解的图像融合框架。对源图像进行主成分分析,依据前几个主成分重建图像,经过下采样过程得到近似图像,对近似图像进行上采样,得到上层图像的差异图像(即细节图像),将最底层近似图像与各层细节图像进行累加完成图像的重构。实验结果表明,该方法能保持图像细节,具有较好的融合效果。
关键词:
图像融合,
主成分分析,
近似图像,
细节图像,
多尺度分解
Abstract: This paper proposes an image fusion framework based on Principal Component Analysis(PCA) decomposition. PCA is applied to the source images; then approximate images are acquired after subsampling the image reconstructed with the first few components; the differences between current approximate image and the last approximate image construct the detail image; the last approximate image and all of the detail images are merged into a new fused image. Experimental results demonstrate that this framework is able to get good performances in image fusion by keeping more details.
Key words:
image fusion,
Principal Component Analysis(PCA),
approximate image,
detail image,
multi-scale decomposition
中图分类号:
潘瑜, 孙权森, 夏德深. 基于PCA分解的图像融合框架[J]. 计算机工程, 2011, 37(13): 210-212.
BO Yu, SUN Quan-Sen, JIA De-Shen. Image Fusion Framework Based on PCA Decomposition[J]. Computer Engineering, 2011, 37(13): 210-212.