基于小波变换和彩色变换的多聚焦图像融合

Multi-focus Image Fusion Based on Wavelet Transform and Color Transform

提出一种结合小波变换及彩色空间变换的多聚焦图像融合方法。首先把彩色图像从RGB空间变换到YIQ空间,将颜色分量与亮度分量进行分离,从而克服RGB空间各颜色分量的相关性造成融合后图像颜色信息的丢失和错乱;接着,将待融合的多聚焦图像进行小波分解以刻画图像的多尺度信息,在小波域实现融合处理。在融合策略的选取上,对高频分量与低频分量分别采取局部方差与局部梯度最大的融合规则,同时以亮度分量Y作为衡量标准,通过一致性检测对融合系数做进一步的优选,以保持融合后图像的区域连续性。实验表明,该方法的融合结果无论在视觉质量及定量指标上都明显优于传统方法。

In this paper, a multi-focus color image fusion method based on combination of wavelet transform and color transform is proposed.This method firstly converts color image from RGB space to the YIQ space,so color component and luminance component are separated, thus overcomes the loss and confusion of the image color information,which caused by the correlation of each color compo.,lent after image fusion.Then, the fusion in wavelet domain is achieved, and multi-focus color image has wavelet decomposition to depict the image information on muhi-scale. On the fusion strategy selection, the high-frequency component and low-frequency component respectively adopts the fusion rule of local variance and local gradient maximum.At the same time ,with the luminance component Y as a measure,the further optimization of fusion coefficient is implemented through the consistency examination toto maintain area continuity after fusion image.Experiments show that the fusion results of the method is obviously superior to traditional methods both on the visual quality and quantitative index.