Karhunen-Loeve及多尺度金字塔联合变换的彩色逆半调算法

Color Inverse Halftoning Algorithm Based on K-L and Multi-Scale Pyramid Transform

红绿蓝（RGB）颜色空间中的各颜色分量具有高度相关性,直接分通道实施的彩色逆半调方法会残留大量人眼敏感的半调纹理,且逆半调图像色偏较大。从分析矢量误差分散半调系统模型入手,推导其加噪特性,针对性地提出了一种Karhunen-Loeve（K-L）及多尺度金字塔联合变换的彩色逆半调算法。算法以K-L变换减弱彩色分量相关性,再利用多尺度中值金字塔算子以及维纳（Wiener）滤波分离并抑制高频细节子图中的半调噪声,最后进行中值金字塔、K-L逆变换重构结果图像。实验表明,该算法能有效去除半调噪声、减小重建图像的颜色偏差,与直接分通道逆半调算法相比峰值信噪比值提高约2~3 dB,且重建图像视觉效果良好。

There is high correlation among each channel in RGB color space. If the color inverse halftoning method with discrete channel is applied there are large worms and color differences which is sensitized by human visual will be left. Based on the model of vector error diffusion the halftoning noise characteristics for color image are developed, and a color inverse halftoning method based on Karhunen-Loeve transform and multi-scale pyramid transform is presented. Using the Karhunen-Loeve transform the correlation among color components are reduced, then the halftoning noise in high frequency detail is separated and de-noised by multi-scale median interpolating pyramid transform and Wiener filter. Finally the color inverse halftone is constructed from the inverse pyramid and Karhunen-Loeve transform. Experimental results demonstrate the proposed method can remove halftoning noise effectively and overcome chromatic aberration. Peak signal-to-noise ratio is increased for about 2-3 dB higher than the color inverse halftoning method with disrete channel, and the excellent visual effect is obtained.