In certain applications, fingerprint authentication systems require templates to be stored in databases. The possible leakage of these fingerprint templates can lead to serious security and privacy threats. Therefore, with the frequent use of fingerprint authentication on mobile devices, it has become increasingly important to keep fingerprint data safe. Due to rapid developments in optical equipment, biometric systems are now able to gain the same biometric images repeatedly, so strong features can be selected with precision. Strong features refer to high-quality features which can be easily distinguished from other features in biometric raw images. In this paper, we introduce an algorithm that identifies these strong features with certain probability from a given fingerprint image. Once values are extracted from these features, they are used as the authentication data. Using the geometric information of these strong features, a cancelable fingerprint template can be produced, and the process of extracting values and geometric information is further explained. Because this is a light-weight authentication scheme, this template has practical usage for low performance mobile devices. Finally, we demonstrate that our proposed schemes are secure and that the user’s biometric raw data of the fingerprint are safe, even when the mobile device is lost or stolen.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.