How can I calculate the IoU between the original image and the predicted one as shown in attached image?

Question

yasmin ismail 2023-9-27

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/2026537-how-can-i-calculate-the-iou-between-the-original-image-and-the-predicted-one-as-shown-in-attached-im

评论： yasmin ismail 2023-10-8

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Shreeya 2023-9-28

Hi @yasmin ismail

I understand that you want to calculate the IoU score between the original and predicted images using MATLAB. You can use the "evaluatesemanticsegmentation" function for this purpose. The input argument provided to the function are "dsResults" and "dsTruth" which refer to the predicted and ground truth images respectively. The output is a semantic segmentaion metrics object with GlobalAccuracy, MeanAccuracy, MeanIoU, and WeightedIoU as the default metrics.

You can refer to the documentaion linked below for more details: https://www.mathworks.com/help/vision/ref/evaluatesemanticsegmentation.html#d126e248885

Hope this helps!

3 个评论
显示 1更早的评论隐藏 1更早的评论

yasmin ismail 2023-9-28

@Shreeya thanks for your help but I need some clarification for your previouse sggestion function as following: If the following algorithim is the one that I used for crack detction to get the attached output image:

% Program to compute the mean width of a blob in an image.

clearvars;

close all;

clc;

fontSize = 15;

% Read in original image, with white lightning on black background.

baseFileName = 'Original image.jpg';

fullFileName = fullfile(pwd, baseFileName);

grayImage = imread(fullFileName);

% Get the dimensions of the image.

% numberOfColorChannels should be = 1 for a gray scale image, and 3 for an RGB color image.

[rows, columns, numberOfColorChannels] = size(grayImage)

if numberOfColorChannels > 1

% It's not really gray scale like we expected - it's color.

% Use weighted sum of ALL channels to create a gray scale image.

% grayImage = rgb2gray(rgbImage);

% ALTERNATE METHOD: Convert it to gray scale by taking only the green channel,

% which in a typical snapshot will be the least noisy channel.

grayImage = grayImage(:, :, 2); % Take green channel.

else

grayImage = grayImage; % It's already gray scale.

end

% Now it's gray scale with range of 0 to 255.

subplot(2, 3, 1);

imshow(grayImage, [])

impixelinfo; % Let user mouse around and see values in the status line at the lower right.

title('Original Image', 'FontSize', fontSize);

% Binarize the image.

% mask = imbinarize(grayImage);

lowThreshold = 0;

highThreshold = 160;

% Interactively and visually set a threshold on a gray scale image.

% https://www.mathworks.com/matlabcentral/fileexchange/29372-thresholding-an-image?s_tid=srchtitle

[lowThreshold, highThreshold] = threshold(lowThreshold, highThreshold, grayImage);

mask = grayImage >= lowThreshold & grayImage <= highThreshold;

% Fill holes.

mask = imfill(mask, 'holes');

% Take largest blob only.

mask = bwareafilt(mask, 1);

subplot(2, 3, 2);

imshow(mask)

impixelinfo; % Let user mouse around and see values in the status line at the lower right.

title('Mask', 'FontSize', fontSize)

% Compute the skeleton

skelImage = bwskel(mask);

subplot(2, 3, 3);

imshow(skelImage)

impixelinfo; % Let user mouse around and see values in the status line at the lower right.

title('Thinned', 'FontSize', fontSize)

thus mean, if I have 100 images for example , i have to input each one as ground truth (original image-attached one) and save each ouptput from the model and make a dataset consist of each output and input , then enter them to "evaluatesemanticsegmentation" function to get GlobalAccuracy, MeanAccuracy, MeanIoU, and WeightedIoU.

Is it right or not?

yasmin ismail 2023-10-3

@Shreeya how can I apply semantic segemnetation or any method by matlab to calculate the IoU bewtwwen the attached groundTruth(crack) ande the attacehed nodel outPut?

yasmin ismail 2023-10-8

@Shreeya I created an image truth and I tried to use evaluatesemanticsegmentation function as shown in

Evaluate semantic segmentation data set against ground truth - MATLAB evaluateSemanticSegmentation (mathworks.com) as follow:

destinationTestLabels = "D:\Matlab pics\matlab practices21\Phd analysis\trial meyhods\GroundTruth\crack\testLabels";

destinationTestImages = "D:\Matlab pics\matlab practices21\Phd analysis\trial meyhods\GroundTruth\crack\testImages";

testImagesDir = fullfile(destinationTestImages,'testImages');

testLabelsDir = fullfile(destinationTestLabels,'testLabels');

pixelLabelID = [1 0];

classNames = ["crack" "background"];

imds = imageDatastore(destinationTestImages);

pxdstest11 = pixelLabelDatastore(destinationTestLabels,classNames,pixelLabelID,"FileExtensions",".png");

data = load('triangleSegmentationNetwork');

net = data.net

pxdsResults = semanticseg(imds,net,"WriteLocation",tempdir);

metrics = evaluateSemanticSegmentation(pxdsResults,pxdsTruth);

metrics

metrics.ClassMetrics

Then I got the following error:

Error using SeriesNetwork/activations (line 817)

The spatial dimension sizes [313 316 3] of the input images to layer 'imageinput' must be greater than

or equal to the corresponding minimum input dimension sizes of the layer [32 32 1].

Error in semanticseg>iPredictDAGSeriesNetwork (line 609)

allScores = activations(net, X, layerName, ...

Error in semanticseg>iClassifyImagePixels (line 556)

allScores = iPredictDAGSeriesNetwork(X, net, params);

Error in semanticseg>iProcessImageDatastoreSerially (line 938)

L = iClassifyImagePixels(X{i}, net, params);

Error in semanticseg (line 265)

filenames = iProcessImageDatastoreSerially(ds, net, params);

Error in Gtruth3 (line 11)

pxdsResults = semanticseg(imds,net,"WriteLocation",tempdir);

I already hve two files testImages and testLabels and each will contain 100 or more of groundTruth and testImages and all shoud enter semantic segemnation not only the attached images ,

How can I fix it to calculate IoU??

请先登录，再进行评论。

How can I calculate the IoU between the original image and the predicted one as shown in attached image?

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

回答（1 个）

3 个评论
显示 1更早的评论隐藏 1更早的评论

另请参阅

类别

标签

产品

版本

Community Treasure Hunt

How can I calculate the IoU between the original image and the predicted one as shown in attached image?

0 个评论 显示 -2更早的评论隐藏 -2更早的评论

回答（1 个）

3 个评论 显示 1更早的评论隐藏 1更早的评论

另请参阅

类别

标签

产品

版本

Community Treasure Hunt

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

3 个评论
显示 1更早的评论隐藏 1更早的评论