Features extraction

My task is to cluster some images, I decided to use the VGG model to extract the features and then use K-Means to cluster these features.

When I use a VGG as a feature extractor, I should make sure if the VGG model was trained on this type of data before, otherwise, the VGG model is not generalizable to all types of data, am I right?

I am looking for a general method to cluster images regardless of the type of dataset efficiently.
If you know any efficient image-based clustering methods, could you please point them out?

1 Like

Have you tried the links below?

How to cluster images based on visual similarity
Use a pre-trained neural network for feature extraction and cluster images using K-means.

Tim Horton Repo using Keras

Autoencoders can be used to learn a compressed representation of images. Once you get the feature vector, use some standard clustering algorithms like k-means. If you don’t know the number of clusters, use elbow method.

1 Like

Hey! I am looking to implement this myself.
I wanted to check if using a pretrained model (Essentially trying to leverage something like ImageNet) to create these compressed representations will help my case? If yes, which Pretrained Models should I be looking at.

Thanks in advance

Category icons made by Freepik from www.flaticon.com