Image retrieval describes the problem of finding, within a large database, images containing the same or similar objects as a given query image. This article is meant to provide a short reading list for image retrieval by focussing on the associated subproblems: image description, descriptor compression, nearest-neighbor search and query expansion.
Ochs et al. proposed iPiano, a proximal algorithm with inertial force for non-convex and non-smooth optimization. This article presents a C++ implementation which was written as part of a seminar on “Selected Topics in Image Processing”.