0
$\begingroup$

I am trying to build a classifier for a specific card dataset let's say cards or no cards. I am using Mobilenet trained on Imagenet dataset as my classifier and further training it on my dataset. I am able to train it, and it's performance is quite good on the dataset. Let's say my card has for different regions of interest as shown below:- enter image description here

It is able to perfectly recognize the above passed image as card.

But I am able to fool my classifier if I change the ordering of the regions of card and then giving it to classifier as shown below:- enter image description here

I want the classifier to learn the exact occurrences of features of cards as in First Image so that if I alter them it should be able to reject that card (like in second image).

Is there any way to achieve this?

$\endgroup$
0
$\begingroup$

You could try a recurrent neural network classifier.

Alternatively, and perhaps more easily, augment your dataset to contain images of cards with changed ordering of the card images, and train on the resulting dataset.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.