基于二代Curvelet变换与MPCA的可见光与红外图像融合

针对同一场景红外图像与可见光图像的融合问题,提出了一种基于二代Curvelet变换与模块化主成分分析(MPCA)的图像融合新方法。首先对原始图像分别进行快速离散Curvelet变换,得到不同尺度和方向下的粗细尺度系数;根据红外图像与可见光图像的不同物理特性以及人类视觉系统特性,对粗尺度系数的选择,采用基于模块化主成分分析(MPCA)的融合规则,确定融合权值,而对不同尺度与方向下的细尺度系数的选择,采用基于局部区域能量的融合规则;最后经Curvelet逆变换得到融合结果。实验结果表明,该方法能够更加有效、准确地提取图像中的特征,在主观视觉效果与客观评价指标上均取得了较好的融合效果,是一种可行有效的图像融合算法。

Fusion of infrared and visible images based on the second generation Curvelet transform and MPCA

For the fusion problem of infrared and visible light images with the same scene, an image fusion algorithm based on the second generation Curvelet and Modular Principal Component Analysis (MPCA) was proposed. Firstly, the fast discrete Curvelet transform was performed on the original images to obtain coarse scale and fine scale coefficients at different scales and in various directions respectively. Secondly, according to the different physical features of infrared and visible light images and human visual system features, the fusion weights were determined by MPCA method for coarse scale coefficients; while the fusion rule based on local region energy was used for fine scale coefficients. Finally, the fusion results were obtained through the inverse Curvelet transform. The experimental results illustrate that the proposed algorithm is effective for extracting the characteristics of the original images and has better fusion results than others in the subjective visible effect and objective evaluation index.