Multi-Biometrics Recognition Research Of The Human Face And Ear

Biometric systems deployed in current real-world applications are primarily unimodal, i.e., they depend on the evidence of a single biometric marker for personal identity authentication (e.g., single ear or face). Unimodal biometrics are limited, because no single biometric is generally considered both sufficiently accurate and robust to hindrances caused by external factors.Several of the limitations imposed by unimodal biometric systems can be overcome by incorporating multiple biometric markers for performing authentication. Such systems, known as multimodal biometric systems, are expected to be more reliable due to the presence of multiple, independent pieces of evidence. However, the incorporation of multiple biometric markers can also lead to additional complexity in the design of a biometric system. For instance, a technique, known as data fusion, must be employed to integrate multiple pieces of evidence to infer identity.Fusion at this match score level has the advantage of utilizing as much information as possible from each biometric modality. There are several motivations for developing a multi-modal ear and face biometric system. Firstly, the ear and face data can be captured using conventional cameras. Secondly, the data collection for face and ear is non-intrusive. Thirdly, the ear and face are in close physical proximity to each other and when acquiring data of the ear (face) the face (ear) is frequently encountered as well. Thus, a multi-modal face and ear biometric system is more feasible than, say, a multi-modal face and fingerprint biometric system.In this paper,we fuse data at this match score level,extract feature with PCA, normalize the feature vector with Min-Max and Tanh-Estimator, respectively.Last, We use DS and weighted sum to fuse the results at the score level.By fusing the face and ear biometric, the former of the performance of the system is increased to 97.5% and the latter is 100%. For reducing illumination and contrast affection, we propose an ear recognition method of phase congruency and KDDA combination. The results of the experiments show the effectiveness of this approach. Based on the above discussion we present a multi-modal ear and face biometric system.