Fuzzy cyclic random mapping for face recognition based on MD-RiuLBP feature

Authors:
Wu Yichen;Fang Yuchun;Tan Ying
Affiliations:
School of Computer Engineering and Science, Shanghai University, Shanghai, China;School of Computer Engineering and Science, Shanghai University, Shanghai, China;School of Computer Engineering and Science, Shanghai University, Shanghai, China
Venue:
CCBR'11 Proceedings of the 6th Chinese conference on Biometric recognition
Year:
2011

Citing 7
Cited 0

A fuzzy commitment scheme

CCS '99 Proceedings of the 6th ACM conference on Computer and communications security
Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Fuzzy Vault Scheme

Designs, Codes and Cryptography
Random Multispace Quantization as an Analytic Mechanism for BioHashing of Biometric and Random Identity Inputs

IEEE Transactions on Pattern Analysis and Machine Intelligence
An analysis of BioHashing and its variants

Pattern Recognition
A Novel Face Hashing Method with Feature Fusion for Biometric Cryptosystems

ECUMN '07 Proceedings of the Fourth European Conference on Universal Multiservice Networks
Fusion of multi-directional rotation invariant uniform LBP features for face recognition

IITA'09 Proceedings of the 3rd international conference on Intelligent information technology application

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a novel face-hashing algorithm named Fuzzy Cyclic Random Mapping (FCRM) and utilize it with our previously proposed Multi-directional Rotation Invariant Uniform Local Binary Pattern (MD-RiuLBP) feature for both face authentication and identification. The kernel part of the FCRM is a cyclic random mapping process. The fault-tolerant technology is also introduced in the FCRM to reduce the impact of random noise existing in the face features. Several popular face features are compared to verify the effectiveness of FCRM. Experiments show that the FCRM performs the best when using the MD-RiuLBP feature. Experimental results prove that the proposed FCRM takes into consideration both the security and the fault tolerance and can prevent the imposters while keeping high accuracy.