5
$\begingroup$

Suppose I have a set of characters with both natural scene and synthetic images, and another set with only synthetic images. I'd like to make a classifier which is trained on only on this data and tested on natural scene images of characters from the second set. Does anyone know of an approach that give good test accuracy in such case?

Example:

Synthetic digits:

enter image description here

Natural scene digits:

enter image description here

Synthetic thai characters:

enter image description here

Natural scene thai characters: (not present during training)

$\endgroup$

Your Answer

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

Browse other questions tagged or ask your own question.