Multimodal Biometric Database and its Privacy Protection

Conference: McGraw-Hill International Conference on Signal, Image Processing Communication and Automation
Author(s): Raju A S, V Udayashankara Year: 2017
Grenze ID: 02.MH-ICSIPCA.2017.1.87 Page: 557-564

Abstract

Multimodal biometric authentication requires fusion of information extracted from different biometric modalities.\nFace recognition is the most common and versatile biometric parameter used for years. Recently, bio-signals such as\nelectrocardiogram (ECG), photoplathysmogram etc. are under study for probable use in authentication work. It is also\nestablished that multi-parameter approach in biometric analysis plays a vital role in increasing accuracy and robustness and\npreventing spoofing in spite of more computational demand. In the present study, information fusion based authentication\nsystem is proposed using face, fingerprint and ECG. Instead of conventional face image, a unique frontal face textural signal\nis proposed. This leads to simpler data processing similar to that of ECG signal. Finally, information from both the signals is\nfused at mother template generation level. The aim of this paper is to summarize the common attacks against biometric\nsystems (fake biometrics, template modification etc.) and discuss techniques that can be used to counter them. The features\nthat extracted from the biometric samples considered a critical part of biometric system which is called biometric template.\nTemplate security schemes are dependent on the overall performance parameters of the system and must be computationally\nhard to avoid modality reconstruction.

<< BACK

MH-ICSIPCA - 2017