基于最大加权投影求解的彩色图像灰度化对比度保留算法  

Maximum Weighted Projection Solver for Contrast Preserving Decolorization

作　　者：卢红阳[1] 刘且根[1] 熊娇娇[1] 王玉皞[1] 邓晓华[1] 

机构地区：[1]南昌大学信息工程学院,南昌330031

出　　处：《自动化学报》2017年第5期843-854,共12页Acta Automatica Sinica

基　　金：国家自然科学基金(61362001)资助~~

摘　　要：针对目前彩色图像灰度化难以充分保留原彩色图像对比度的问题,本文提出了基于最大加权投影求解的彩色图像灰度化模型及算法.首先,在好的彩色图像灰度化算法应使灰度化图像具有最大对比度的假设下,本模型提出最大加权投影的目标优化函数,并且将原始彩色图像梯度权重引入到最大化函数中,使得原彩色图像中对比度较小的区域也能够在灰度化后的图像中得到保持.每个彩色通道梯度的高斯加权系数反映灰度图像的对比度和原彩色图像的颜色顺序.其次,对所提模型使用参数离散搜索策略求解,通过对线性离散参数模型产生的候选图像进行搜索,由于只有几个算术运算,计算速度较快.最后,为评价所提出算法在复杂场景下图像灰度化对比度保持性能,本文对Cadik、CSDD和COLOR250数据集分别进行灰度化实验.定性和定量实验结果表明,所提算法相比于其他算法能较好地保留原彩色图像颜色对比度,同时具有对噪声鲁棒和运算速度快的优势.This paper presents a color-to-gray conversion model for faithfully preserving the contrast details of the original color image. First, on the basic assumption that a good gray conversion should make the conveyed gradient values to be maximal, we present a maximum weighted projection function to model the decolorization procedure, incorporating weights of the original gradients into the maximization problem. The Gaussian weighted factor consisting of the gradients of indivisual channels of the input color image is employed to better reflect the degree of preserving feature discriminability and color ordering. Second, a discrete searching solver is proposed by determining the solution with the loss function value from the linear parametric model-induced candidate images. The non-iterative solver has advantages in simplicity and speed with only several simple arithmetic operations, leading to real-time computational speed. Finally, extensive experimental evaluations on the existing datasets show that the proposed method outperforms the state-of-the-art methods quantitatively and qualitatively.

关 键 词：彩色图像灰度化 最大加权投影 对比度保留 线性参数模型 离散搜索 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]