基于再生核空间的自适应图像彩色化算法

Adaptive Image Colorization Based on Reproducing Kernel Hilbert Spaces

针对传统的图像彩色化算法中彩色化结果质量不佳、参数设置不合理等问题,提出一种新的基于再生核空间的自适应灰度图像彩色化算法.该方法通过求泛函极值建立非线性方程,设置与图像像素亮度相关的自适应再生核,用最小二乘法对方程进行数值求解得到彩色化结果.与其他灰度图像彩色化技术相比,该方法能在自适应选择参数的同时,有效提高图像彩色化质量.

An adaptive image colorization algorithm based on reproducing kernel Hilbert spaces is proposed in this paper aiming at overcoming unsatisfactory and inefficiency in the traditional colorization algorithm. A nonlinear equation is established through minimization of a functional. By choosing adaptive reproducing kernel related to the image properties. A colorized image is obtained by numerically solving the equation with a least-square approach. The simulation results show that the proposed algorithm outperforms previous method in improving the image quality and selecting adaptive parameter.