Sparse representations and Random Projections for robust and cancelable biometrics

TitleSparse representations and Random Projections for robust and cancelable biometrics
Publication TypeConference Papers
Year of Publication2010
AuthorsPatel VM, Chellappa R, Tistarelli M
Conference NameControl Automation Robotics Vision (ICARCV), 2010 11th International Conference on
Date Published2010/12//
KeywordsBiometric identification, Cancelable Biometrics, Compressed sensing, face data, face recognition, iris data, iris recognition, personal biometric data, Random Projections, robust biometrics, sparse representations

In recent years, the theories of Sparse Representation (SR) and Compressed Sensing (CS) have emerged as powerful tools for efficiently processing data in non-traditional ways. An area of promise for these theories is biome #x0301;trie identification. In this paper, we review the role of sparse representation and CS for efficient biome #x0301;trie identification. Algorithms to perform identification from face and iris data are reviewed. By applying Random Projections it is possible to purposively hide the biome #x0301;trie data within a template. This procedure can be effectively employed for securing and protecting personal biome #x0301;trie data against theft. Some of the most compelling challenges and issues that confront research in biometrics using sparse representations and CS are also addressed.