Indexing Irises by Intrinsic Dimension

TL;DR

This paper demonstrates that iris images can be effectively indexed in a four-dimensional intrinsic space, enabling rapid identification by reducing the search to a small neighborhood in this space.

Contribution

It introduces a method to measure the intrinsic dimension of iris features and uses PCA for efficient indexing and matching in iris identification systems.

Findings

Intrinsic dimension of iris key portions is about four.

Indexing in 4D space allows quick identification.

Matching requires comparison to only a small fraction of the database.

Abstract

28,000+ high-quality iris images of 1350 distinct eyes from 650+ different individuals from a relatively diverse university town population were collected. A small defined unobstructed portion of the normalized iris image is selected as a key portion for quickly identifying an unknown individual when submitting an iris image to be matched to a database of enrolled irises of the 1350 distinct eyes. The intrinsic dimension of a set of these key portions of the 1350 enrolled irises is measured to be about four (4). This set is mapped to a four-dimensional intrinsic space by principal components analysis (PCA). When an iris image is presented to the iris database for identification, the search begins in the neighborhood of the location of its key portion in the 4D intrinsic space, typically finding a correct identifying match after comparison to only a few percent of the database.