Lucene/Solr Revolution 2017

Facial recognition in production is difficult because neural networks are slow and expensive to train, and must be retrained to recognize new faces added to the set. Older approaches which address these issues such as eigenfaces exist don’t scale as they require a matrix decomposition. Apache Mahout offers a distributed singular value decomposition method, which scales to matrices of arbitrary sizes on Apache Spark, making it possible to use the older yet still powerful Eigenfaces approach to recognize and add new faces in near real time (with the help of Solr).

In this talk we present a full stack lambda-style facial recognition system. The offline component uses Apache Mahout to compute the eigenfaces. The online component identifies faces in an image with an interchangeable module, decomposes the face into a linear combination of the eigenfaces, searches for a matching face using SOLR, and if no match is found adds the face as a “new face”.