PIQE
Perception based Image Quality Evaluator (PIQE) no-reference image quality score
描述
[
还返回从输入图像计算出的空间质量掩码。score
,ActivityMask
,noticeableArtifactsMask
,NOISEMASK
] = piqe(A
)
例子
Input Arguments
Output Arguments
算法
PIQE
calculates the no-reference quality score for an image through block-wise distortion estimation, using these steps:
计算图像中每个像素的平均对比度归一化(MSCN)系数,使用N. venkatanath和其他提出的算法计算图像中的每个像素[1]。
Divide the input image into nonoverlapping blocks of size 16-by-16.
Identify high spatially active blocks based on the variance of the MSCN coefficients.
Generate
ActivityMask
使用确定的高空间活动块。In each block, evaluate distortion due to blocking artifacts and noise using the MSCN coefficients.
使用阈值标准将块分类为扭曲的块,上面有封锁的伪影,带有高斯噪声的扭曲块和未发生的块。
Generate
noticeableArtifactsMask
from the distorted blocks with blocking artifacts andNOISEMASK
从高斯噪音的扭曲块中。Compute the PIQE score for the input image as the mean of scores in the distorted blocks.
这quality scale of the image based on its PIQE score is given in this table. The quality scale and respective score range are assigned through experimental analysis on the dataset in LIVE Image Quality Assessment Database Release 2[2]。
质量量表 | 得分范围 |
优秀的 | [0,20] |
Good | [21, 35] |
公平的 | [36, 50] |
Poor | [51, 80] |
坏的 | [81, 100] |
参考
[1]
[2]