主要内容

装饰

Fit custom model for BRISQUE image quality score

所有的页面崩溃

Syntax

model = fitbrisque(imds,opinionScores)

Description

example

model= fitbrisque（imds,opinionScores)creates a Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) model from a reference image datastore,imds, with corresponding human perceptual differential mean opinion score (DMOS) values,opinionScore.

Note

To use the装饰功能，您必须具有统计信息和机器学习工具箱™。

Examples

collapse all

This example uses:

打开实时脚本

从一组质量感知的功能和相应的人类意见分数中训练定制的野蛮模型。使用自定义模型来计算自然场景图像的棕褐色分数。

Save images from an image datastore. These images all have compression artifacts resulting from JPEG compression.

setDir = fullfile(toolboxdir('图片'),'imdata');imd = imageDatastore (setDir,“ fileextensions'，{'.jpg'});

Specify the opinion score for each image. The following differential mean opinion score (DMOS) values are for illustrative purposes only. They are not real DMOS values obtained through experimentation.

opinionScores = 100*rand(1,size(imds.Files,1));

使用图像数据存储和意见分数创建质量感知功能的自定义模型。由于得分是随机的，因此属性值将有所不同。

model = fitbrisque(imds,opinionScores')
Extracting features from 38 images. ..... Completed 14 of 38 images. Time: Calculating... ......Training support vector regressor... Done.
model = brisqueModel with properties: Alpha: [35x1 double] Bias: 58.1331 SupportVectors: [35x36 double] Kernel: 'gaussian' Scale: 0.2766

Read an image of a natural scene that has the same type of distortion as the training images. Display the image.

I = imread('car1.jpg');imshow(I)

Figure contains an axes object. The axes object contains an object of type image.

Calculate the BRISQUE score for the image using the custom model. Display the score.

布里斯克I = brisque(I,model); fprintf('BRISQUE score for the image is %0.4f.\n'，布里斯基）
BRISQUE score for the image is 72.7539.

Input Arguments

collapse all

参考图像数据存储，指定为ImageDatastore目的。The datastore must contain 2-D grayscale or 2-D RGB images of data typesingle,double,INT16,uint8, oruint16. The images must have a known set of distortions such as compression artifacts, blurring, or noise.

人类意见分数，指定为具有值[0，100]的值的数字向量。每个元素中的元素opinionScores是与数据存储中图像相对应的人类感知DMOS值imds. The length ofopinionScoresis equal to the number of images inimds.

Data Types:single|double|int8|INT16|int32|uint8|uint16|uint32

Output Arguments

collapse all

Custom model of image features, returned as a布里斯克Model目的。modelcontains a support vector regressor (SVR) with a Gaussian kernel trained to predict the BRISQUE quality score.

参考

[1]Mittal, A., A. K. Moorthy, and A. C. Bovik. "No-Reference Image Quality Assessment in the Spatial Domain."IEEE Transactions on Image Processing. Vol. 21, Number 12, December 2012, pp. 4695–4708.

[2]Mittal, A., A. K. Moorthy, and A. C. Bovik. "Referenceless Image Spatial Quality Evaluation Engine." Presentation at the 45th Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, November 2011.

Version History

Introduced in R2017b

See Also

Functions

Objects

Topics