Image Embedding

Given a picture of an object, it assigns a N-Dimensional vector which encodes its semantic information. When given two different pictures of the same object, both points are near. Conversely, when given two images of different objects, their points are far away. The user can then choose an epsilon radius to decide if two images belong to the same object. This approach allows for quick learning of new, unseen classes.

Upload an image (.jpg or .png). Max size: 1.0 MB: