基于NSST域灰度关联分析的多聚焦图像融合方法

根据多聚焦图像的成像特点,并利用非下采样剪切波变换(non-subsample shearlet transform,NSST)在图像融合领域的优势,将非下采样剪切波变换运用于多聚焦图像融合.由于NSST会将图像分解为一幅低频图像和若干幅高频图像,对于低频图像采用了基于标准差的融合策略,而针对高频图像的特点,利用灰度关联分析在图像融合中的优势,将其运用在高频图像的融合中.后将低频图像和高频图像的融合图像进行NSST的逆变换后得到了融合图像.计算机仿真实验表明:相比于传统的剪切波交换,本文提出的图像融合方法提高图像的融合质量,增加了图像的信息量,具有一定的有效性和实用性.

Fusion technique for multi-focus image based on analysis of grey relation in NSST domain

The non-subsample shearlet transform (NSST) is used for the multi-focus image fusion according to its advantage in image fusion. NSST can decompose an image into a low frequency image and several high frequency images. Then, the low frequency image can be fused by strategies based on standard deviation, while the high frequency images are fused by gray correlation analysis. The inverse transformation of NSST is applied to the processed low and high frequency images respectively to get the final image. The simulation validates the efficiency and feasibility of the proposed method in this paper and proves that compared to the traditional shearlet transform, it advances the quality of image fusion, increases the image information.