Hugo Proença, Member, IEEE
Abstract: Recent advances in the deployment of biometric systems at large scale identification scenarios augmented the interest in indexing / retrieval strategies. In this paper it is proposed a technique that operates at the IrisCode level. Gallery codes are decomposed at multiple scales and, based on the most reliable components of each one, the position of the corresponding identity in nodes of a n-ary tree determined. In retrieval, the probe is similarly decomposed and the distance to multi-scale centroids used to privilege paths on the tree. This way, for each query only a small number of branches are traversed up to the last level, which nodes most times contain the identity of interest. When compared with indexing strategies that operate at the code level, the proposed method behaves comparably on good-quality data and shows higher robustness when handling degraded codes, Lastly, the temporal computational requirements of the proposed strategy are discussed and compared with related techniques.
Fig. 1: Cohesive perspective of the indexing structure and of the data retrieving strategy. For a query s with credits ξ(0), the distance between the decomposition of s at top level of (s(4)) to the centroids is used to generate the new generation of credit scores (ξ(1)). For any branch with negative values, the search is stopped, meaning that all subsequent levels in the tree are not traversed (illustrated by gray nodes). During the traversal of the tree, every identity found at any level with ξ(.) > 0 is included in the retrieved set of identities. The cross marks denote nodes where the search process stops.
Reproducible Research
(Source code soon released)
Abstract: Recent advances in the deployment of biometric systems at large scale identification scenarios augmented the interest in indexing / retrieval strategies. In this paper it is proposed a technique that operates at the IrisCode level. Gallery codes are decomposed at multiple scales and, based on the most reliable components of each one, the position of the corresponding identity in nodes of a n-ary tree determined. In retrieval, the probe is similarly decomposed and the distance to multi-scale centroids used to privilege paths on the tree. This way, for each query only a small number of branches are traversed up to the last level, which nodes most times contain the identity of interest. When compared with indexing strategies that operate at the code level, the proposed method behaves comparably on good-quality data and shows higher robustness when handling degraded codes, Lastly, the temporal computational requirements of the proposed strategy are discussed and compared with related techniques.
Fig. 1: Cohesive perspective of the indexing structure and of the data retrieving strategy. For a query s with credits ξ(0), the distance between the decomposition of s at top level of (s(4)) to the centroids is used to generate the new generation of credit scores (ξ(1)). For any branch with negative values, the search is stopped, meaning that all subsequent levels in the tree are not traversed (illustrated by gray nodes). During the traversal of the tree, every identity found at any level with ξ(.) > 0 is included in the retrieved set of identities. The cross marks denote nodes where the search process stops.
Reproducible Research
(Source code soon released)
- generateDataSet.m: MATLAB function to generate the synthetic data sets of IrisCodes.
- indexDataSet.m: MATLAB function to create the indexing tree.
- retrieveQuery.m: MATLAB function to retrieve a set of identities, based on a query.
- performanceEvaluation.m: MATLAB function to get hit/penetration values, based on an indexing tree.
- aux.zip: Set of auxiliary functions.
- TR_VWII.pdf: Description of a method to generate synthetic data sets of IrisCodes.