Indexing Irises by Intrinsic Dimension
This is an incremental improvement for biometric identification systems, potentially speeding up iris recognition in security applications.
The paper tackled the problem of efficiently matching iris images by using a small key portion of the iris and mapping it to a 4D intrinsic space via PCA, resulting in a search that typically finds a correct match after comparing to only a few percent of the database.
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.