This is similar to comparing fingerprints but can be described more technically as a distance function for locality-sensitive hashing.
[citation needed] Uses of similarity measures where a twin network might be used are such things as recognizing handwritten checks, automatic detection of faces in camera images, and matching queries with indexed documents.
[4] In its most extreme form this is recognizing a single person at a train station or airport.
The common learning goal is to minimize a distance metric for similar objects and maximize for distinct ones.
Furthermore, using a Fully Convolutional Network, the process of computing each sector's similarity score can be replaced with only one cross correlation layer.