基于人眼视觉系统的图像质量评价方法

Image Quality Evaluation Method Based on Human Visual System

提出了一种基于改进韦伯局部特征的图像质量评价方法。首先,模拟人眼识别图像对比度的机制,改进了灰度优化算法并保留了彩色图像最优对比度;然后模拟人眼识别图像中目标内容轮廓的机制,使用Prewitt算子计算邻域内的梯度方向,并计算邻域内垂直和水平方向的差分激励值并求和,以提取出图像的边缘信息;最后使用支持向量机训练多种数据集中图像的一维特征数据,并构建了图像质量评价模型。实验结果表明,所提方法比人眼识别方法的效果更具一致性,具有准确率高、适用性良好和预测方向性强等优点。

An image quality evaluation method based on improved Weber local features is proposed.First,the mechanism of image contrast recognition by the human visual system is simulated.The improved gray optimization algorithm retains the best contrast of the color image.Then,prewitt operator is used to calculate the gradient direction in the neighborhood.Next,the differential excitation values in the vertical and horizontal directions in the neighborhood are calculated and summed to obtain the edge information of the image.Finally,the support vector machine is used to train the one-dimensional feature data of the images in various databases to construct an image quality evaluation model.Experiments show that the method has the advantages of higher accuracy,better applicability and strong prediction direction.