主要内容

PIQE

Perception based Image Quality Evaluator (PIQE) no-reference image quality score

所有的页面崩溃

Syntax

score = piqe(A)
[score,activityMask,noticeableArtifactsMask,noiseMask] = piqe(A)

描述

example

score= piqe（A)计算图像的无参考图像质量评分Ausing a perception based image quality evaluator. A smaller score indicates better perceptual quality.

example

[score,ActivityMask,noticeableArtifactsMask,NOISEMASK] = piqe（A)还返回从输入图像计算出的空间质量掩码。

例子

全部收缩

打开实时脚本

计算图像的PIQE评分和相应的扭曲图像。用相应的图像显示结果。

在工作区中阅读图像。通过添加噪声和模糊来产生扭曲的图像。采用imnoise生成嘈杂图像的功能imgaussfiltfunction to generate the blurred image.

A = imread('Lighthouse.png'）；anoise = imnoise（a，“高斯”，0,0.05）;ablur = imgaussfilt（a，2）;

计算原始图像和扭曲图像的PIQE分数。

分数= piqe（a）;score_noise = piqe（anoise）;score_blur = piqe（ablur）;

将图像显示为具有相应分数作为图标题的一部分的蒙太奇。

图蒙太奇（{a，anoise，ablur}，'Size'，[1 3]）标题（{[['原始图像​​：piqe分数=', num2str(score),'|嘈杂的图像：PIQE分数=', num2str(score_noise),' '。。。'|模糊图像：PIQE分数='，num2str（score_blur）]}，'FontSize',12)

图包含一个轴对象。带有标题原始图像的轴对象：PIQE得分= 24.8481 |嘈杂的图像：PIQE得分= 72.3643 |模糊图像：PIQE分数= 85.7362包含一个类型图像的对象。

打开实时脚本

Calculate PIQE score of an image distorted due to blocking artifacts and Gaussian noise. Generate spatial quality masks that indicate the high spatially active blocks, noticeable artifacts blocks, and noise blocks in the image. Visualize the spatial quality masks by overlaying them on the distorted image. Display the image with and without the masks and the PIQE score for the image.

将扭曲的图像（由于JPEG2K引起的失真）读取工作空间。

Adistorted = imread('DistortedImage.png'）；

Calculate PIQE score and the spatial quality masks.

[得分，activitymask，noticeableartifactsmask，noisemask] = piqe（Adistorted）;

覆盖输入图像上的空间质量掩码。

mask_1 = labeloverlay（Adistorted，ActivityMask，'Colormap','winter','Transparency'，0.25）;mask_2 = labeloverlay(Adistorted,noticeableArtifactsMask,'Colormap',“秋天”,'Transparency'，0.25）;mask_3 = labeloverlay（Adistort，NoiseMask，'Colormap','hot','Transparency'，0.25）;

显示原始distorted image and the distorted images with overlaid spatial quality masks as a montage.

图蒙太奇（{adistorted，mask_1，mask_2，mask_3}，'Size'，[1 4]）标题（'扭曲图像|叠加活动策略|覆盖noticeableartifactsmask |覆盖noisemask','FontSize',12)

图包含一个轴对象。带有标题扭曲图像的轴对象|叠加活动策略|覆盖noticeableartifactsmask |覆盖NoiseMask包含类型图像的对象。

Display PIQE score for the distorted image.

fprintf('PIQE score for the distorted image is %0.4f.\n',score)
扭曲图像的PIQE得分为65.1855。

Input Arguments

全部收缩

输入图像，指定为大小的2-D灰度图像m-经过-n或大小的2-D RGB图像m-经过-n-by-3。

Data Types:single|双倍的|INT16|uint8|UINT16

Output Arguments

全部收缩

输入图像的PIQE分数A, returned as a nonnegative scalar in the range [0, 100]. The PIQE score is the no-reference image quality score and it is inversely correlated to the perceptual quality of an image. A lowscorevalue indicates high perceptual quality and highscore值表示低感知质量。

Data Types:双倍的

主动块的空间质量面膜，作为大小的2D二进制图像返回m-经过-n， 在哪里m和nare the dimensions of the input imageA。这ActivityMaskis composed of high spatially active blocks in the input image. The high spatially active blocks in the input image are the regions with more spatial variability due to factors that include compression artifacts and noise. The high spatially active blocks are assigned a value'1'在里面ActivityMask。

Data Types:logical

Spatial quality mask of noticeable artifacts, returned as a 2-D binary image of sizem-经过-n， 在哪里m和nare the dimensions of the input imageA。这noticeableArtifactsMaskis composed of blocks inActivityMask包含阻塞伪影（由于压缩）或突然失真。

Data Types:logical

Spatial quality mask of Gaussian noise, returned as a 2-D binary image of sizem-经过-n， 在哪里m和nare the dimensions of the input imageA。这NOISEMASKis composed of blocks inActivityMaskthat contain Gaussian noise.

Data Types:logical

算法

PIQEcalculates the no-reference quality score for an image through block-wise distortion estimation, using these steps:

  1. 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]。

  2. Divide the input image into nonoverlapping blocks of size 16-by-16.

  3. Identify high spatially active blocks based on the variance of the MSCN coefficients.

  4. GenerateActivityMask使用确定的高空间活动块。

  5. In each block, evaluate distortion due to blocking artifacts and noise using the MSCN coefficients.

  6. 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。

  7. GeneratenoticeableArtifactsMaskfrom the distorted blocks with blocking artifacts andNOISEMASK从高斯噪音的扭曲块中。

  8. Compute the PIQE score for the input image as the mean of scores in the distorted blocks.

  9. 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]N. Venkatanath, D. Praneeth, Bh. M. Chandrasekhar, S. S. Channappayya, and S. S. Medasani. "Blind Image Quality Evaluation Using Perception Based Features", In21的会议记录st全国传播会议（NCC）。新泽西州Piscataway：IEEE，2015年。

[2]Sheikh, H. R., Z. Wang, L. Cormack and A.C. Bovik, "LIVE Image Quality Assessment Database Release 2 ",https://live.ece.utexas.edu/research/quality/。

Version History

Introduced in R2018b

See Also

Functions

Topics