一种新的多聚焦彩色图像融合方法

A new method for multi-focus color image fusion

彩色空间变换法是图像融合的经典算法之一,本文提出了一种彩色空间变换与小波变换结合的多聚焦图像融合算法,发挥了两种变换算法的优点。算法首先把源图像变换到YIQ空间,对所有图像的各个颜色分量进行小波分解;对小波分解后的高低频分量采取不同的融合规则,构造小波系数;然后以亮度Y分量作为衡量标准,通过一致性检测得到融合系数;最后进行小波逆变换,再进行YIQ反变换得到融合后的图像。对比实验结果表明,此方法的最佳小波分解层数为2层。最佳小波分解层数越少,图像融合的计算量越小。该方法在减少计算量的同时,也提高了融合质量。融合图像平滑自然,具有很好的视觉效果。

Color space transform is one of typical methods for image fusion. In the paper a newly multi-focus image fusion method that combines advantages of color space transform and wavelet transform is proposed. Firstly, the original images are transformed in YIQ space and are carried on the wavelet decomposition to each color component of all images ; Secondly, we apply different fusion rules to the corresponding high and low frequency component from the wavelet decomposition, thereby the wavelet coefficients are constructed ;Then, the last fusion coefficients are generated based on consistence measurement, in which luminance Y component is used as scale standard;Lastly, we carry on wavelet inverse transform and YIQ inverse transform and the fusion image is obtained. The comparision experiments show that the optimal wavelet decomposition level in this method consists of two levels. The less the optimal wavelet decomposition level is, the less the computational operation of image fusion will be. This method reduces the computational load and improves the quality of image fusion, The fusion image is smooth and good visual effect.