NR-IQA模型的人类视觉系统补偿方法

A compensation method of human visual system based-on NR-IQA

在暗视觉环境下,人类视觉对比度分辨率非常低。针对低照度图像,提出一种基于无参图像质量评价体系的补偿方法(NR-IQA)。首先,建立一种用于提取视觉评价参数的数学模型。其次,建立最好图像质量评价综合函数,用于评价图像补偿的质量。然后,计算评价函数和补偿因子k的数学关系。这种自动寻优方法用于迅速获取暗视觉下的最佳图像质量,特别是在视频图像处理中的实时补偿。

Visual contrast resolution is lower in the low-light level. A compensation method for low-light image based on no-reference image quality assessment （NR-IQA in short） is presented. A mathematical model for extracting vision evaluation parameters is built. The best image quality assessment function is achieved to assess the quality of compensated image. The third step was to get the relationship between the assessment function and the corresponding compensation factors. The method of automatic optimization can be used to quickly acquire the optimal quality from an be taken from scotopic vision, especially image applied to the compensation of video image sequences rapidly.