Complexity of Indexing: Efficient and Learnable Large Database Indexing

Object recognition starts from a set of image measurements (including locations of points, lines, surfaces, color, and shading), which provides access into a database where representations of objects are stored. We describe a complexity theory of indexing, a meta-analysis which identifies the best set of measurements (up to algebraic transformations) such that: (1) the representation of objects are linear subspaces and thus easy to learn; (2) direct indexing is efficient since the linear subspaces are of minimal rank. The index complexity is determined via a simple process, equivalent to computing the rank of a matrix. We readily re-derive the index complexity of the few previously analyzed cases. We then compute the best index for new cases: 6 points in one perspective image, and 6 directions in one para-perspective image; the most efficient representation of a color is a plane in 3D space. For future applications with any vision problem where the relations between shape and image measurements can be written down in an algebraic form, we give an automatic process to construct the most efficient database that can be directly obtained by learning from examples.