Multimodal Access Control: A Review of Emerging Mechanisms

Publication Type:
Smart Innovations in Engineering and Technology, 2019, 15 pp. 183 - 200
Issue Date:
Filename Description Size
Smart+Innovations+in+Engineering+and+Tec.pdfPublished version14.2 MB
Adobe PDF
Full metadata record
Accurately identifying and authenticating a human without requiring proximity, yet with high reliability, is crucial for application areas such as surveillance, dynamic authentication, and proof of identity. While a significant research has been conducted in the direction of human authentication, achieving the authentication in an ambient manner, with high reliability, and security is still far from being perfect under the currently deployed methods. This is due to the requirement of a specific posture and approximation to the device in many approved and deployed methods such as fingerprint, facial recognition, and retinal scan. An ambient authentication system is highly dependent on biometric features that can accurately discriminate between one human and another. These biometric features should be insensitive to variation in posture, proximity, and aging. Extraction of a unique feature set that allows a human to be identified smoothly, even without proximity, under varying conditions is one of the main steps needed for an advancement in this field. In this paper, a review of current and emerging mechanism are provided. A proposed method will use a feature set that allows the system to achieve dynamic detection compared to the currently used technologies such as fingerprint, facial recognition and retinal scan. The proposed feature set is made up of a combination of facial minutiae and thermal contours which are extracted from the human face on-the-fly even without the subject coordination.
Please use this identifier to cite or link to this item: