Bimodal biometrics based on a representation and recognition approach

摘要: It has been demonstrated that multibiometrics can produce higher accuracy than single biometrics. This is mainly because the use of multiple biometric traits subject enables more information to be used for identification or verification. In this paper, we focus on bimodal biometrics and propose a novel representation recognition approach first denotes trait sam- ple by complex vector. Then, it represents test sample through training samples classifies as follows: let expressed linear combination all each being The proposed obtains solu- tion solving system. After evaluating effect, in representing class, into class makes greatest effect. not only but also simple computationally efficient. A large num- ber experiments show our method obtain promising results. C 2011 Society Photo-Optical Instrumentation Engineers (SPIE). (DOI: 10.1117/1.3554740)