CVOct 2, 2012
A Survey of Multibiometric Systems
arXiv:1210.0829v140 citations
Originality Synthesis-oriented
AI Analysis
This is a survey paper, so it is incremental, summarizing existing work rather than introducing new methods.
The paper addresses the limitations of unimodal biometric systems, such as noise and spoof attacks, by proposing multibiometric systems that use multiple independent pieces of evidence to improve reliability.
Most biometric systems deployed in real-world applications are unimodal. Using unimodal biometric systems have to contend with a variety of problems such as: Noise in sensed data; Intra-class variations; Inter-class similarities; Non-universality; Spoof attacks. These problems have addressed by using multibiometric systems, which expected to be more reliable due to the presence of multiple, independent pieces of evidence.