I have a dataset of the periocular region, I have images of the male and female periocular region but they are only labeled as left and right periocular region, Folder is a mixture of male and female periocular region. One can not judge which one is of male and which one is of female periocular region.

According to biometric classification male and female have different periocular regions, so in short, I have only 2 different types of the periocular region (male and female) in my folder as the dataset.

How I can classify them that system automatically separates the feature of the male and female periocular region and train them as 2 different classes.


You can't if you have nothing to start labelling them with.

As you describe it, there's simply no info available (not even about statistics) about the gender of your reference images, so there's nothing you can train.

What you can do is use a different technique (as you say "biometrics say..." I assume there's a non-ML method of classification) and run it over the dataset, and use the resulting labels to train your neural network. Discussion of the sensibility of that is left to you as an exercise for your report!

| improve this answer | |

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