北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2023, Vol. 46 ›› Issue (2): 129-136.

• 模式识别与图像处理 • 上一篇    

基于人眼视觉系统的图像质量评价方法

于天河,柳梦瑶   

  1. 哈尔滨理工大学
  • 收稿日期:2022-03-21 修回日期:2022-05-13 出版日期:2023-04-28 发布日期:2023-05-14
  • 通讯作者: 于天河 E-mail:ythaa@163.com

Image Quality Evaluation Method Based on Human Visual System

  • Received:2022-03-21 Revised:2022-05-13 Online:2023-04-28 Published:2023-05-14

摘要: 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,改进灰度优化算法保留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,计算邻域内垂直和水平方向的差分激励值并取和,提取出图像边缘信息;最后使用支持向量机训练多种数据库中图像的一维特征数据,构建图像质量评价模型。通过对比、验证,表明该方法与人眼的一致性更强,具有准确率较高、适用性良好、预测方向性强等优点。

关键词: 人眼视觉系统, 图像质量评价, 韦伯局部描述符

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

Key words: human visual system, image quality assessment, Weber local descriptor

中图分类号: