How to read an image after a particular result from CNN classification?

1 view (last 30 days)
Hello,
I am working with CNN for Image classification and I have created the code. I am now testing it against a new data and I want to apply a function that would only display the image when the result is a particluar class and I was wondering if I can do it using a FOR LOOP. I am using the following lines of codes for new test data but I am unable to display the image:
newImage= imread('C:\Users\ChawlaV\Desktop\MATLAB\Test Data\AC 4.jpg');
ds = augmentedImageDatastore(inputSize,newImage,'ColorPreprocessing','gray2rgb');
imageFeatures = activations(trainedNet, ds, featurelayer, 'MiniBatchSize', 32,'OutputAs', 'columns');
label = predict(classifier,imageFeatures, 'ObservationsIn','columns');
DistressType = (label); %%there are three classes AlligatorCracks, Potholes and Rutting
For DistressType = Potholes;
imshow(newImage);
end
%% the error that occurs while using this code is as follows:

Accepted Answer

Nomit Jangid
Nomit Jangid on 22 Sep 2020
There are couple of things i'd suggest
  1. If you're comparing DistressType to Potholos, make sure to use '==' (not '=').
  2. label is categorical data so make sure to compare it with some string.
ex; DistressType = 'Potholes'
Since you're not using a 'Potholos' , MATLAB is looking for a variable or function.

More Answers (0)

Products


Release

R2020a

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!