面向彩色增强图像的客观质量评价中国图象图形学报.docVIP

中图法分类号：TN911.73 文献标识码：A 文章编号： 论文引用格式： 面向彩色增强图像的客观质量评价算法 李子印，倪军 中国计量学院光学与电子科技学院, 杭州 310018 摘 要：目的：现有的全参考图像质量评价方法使用“完美”的源信号作为参考，但是增强图像的参考图像通常不是“完美”的。因此，现有的全参考质量评价方法不能用于增强图像的评价，本文提出了一种新的面向彩色增强图像的质量评价算法。方法：本文利用图像的梯度、颜色和亮度特征，提出了增强图像的梯度增强图、颜色增强图和亮度增强因子的计算方法，计算增强图像相对于参考图像在梯度、颜色和亮度方面的增强程度；并建立了亮度增强因子和梯度增强图、颜色增强图之间的关系模型；另外，原图像的梯度和颜色特征也被提取用于增强图像的质量评价。结果：使用公开数据库进行的实验结果表明，该算法和现有最优算法相比，皮尔逊线性相关系数相关系数均方根误差Objective quality assessment for enhanced chromatic images Li Ziyin, Ni jun College of Optical and Electronic Technology, China Jiliang University, Hangzhou, 310018 Abstract: Objective: Image enhancement is very important in various visual signal processing applications. In many applications such as photo retouching, visual inspection, machine analysis and others, image enhancement methods are usually proposed to try to obtain images with better visual quality. In these cases, original images are usually not ‘perfect’. However, existing full-reference image quality assessment methods use ‘perfect’ original images as the reference signals to assess the image quality. Therefore, existing full-reference image quality assessment methods cannot be used well to evaluate the visual quality of enhanced images. In this paper, a novel visual quality assessment metric based on features of gradient, colorfulness and luminance is proposed for enhanced chromatic images. Method: It is well accepted that the human visual system (HVS) is highly sensitive to the gradient information, which can effectively capture both the contrast and structural/texture information. So, in the proposed metric, the gradient enhancement map is calculated by estimating the enhancement degree of the enhanced image compared to its reference image. In addition, colorfulness is widely accepted as the attribute of the perceived color in certain regions appearing to be more or less chromatic. In this proposed metric, the colorfulness of an enhanced image is estimated by two factors: one is the average distance