Meta Platforms, Inc.
Methods and systems for determining image similarity

Abstract:

In particular embodiments, a method includes, by one or more computing devices, receiving an image requiring an administrative action. The method includes, by the one or more computing devices, generating a single large hash value based on the image and a content-aware hashing function. The large hash value has a first number of dimensions. The method includes, by the one or more computing devices, generating a small hash value corresponding to the image from the large hash value using a locality-sensitive hashing function. The small hash value has a second number of dimensions that is smaller than the first number of dimensions. The method includes determining, based on the small hash value corresponding to the image, a cluster center mutually associated with the image. The method includes, by the one or more computing devices, performing the administrative action on one or more images mutually associated with the cluster center.