SESAM: A biometric person identification system using sensor fusion

Abstract

In this paper we describe the person authentification system SESAM. Person identification and verification still is a very difficult task. Using one biometric feature, i. e. the photograph or the sound of the voice, leads to good results, but there is no reliable way to verify the classification. In order to reach robust identification and verification we are combining three different biometric cues. These cues are dynamic, i. e. the sound of the voice and the lip motion, and static, i. e. the fixed image of the face. Each branch is preprocessed and classified separately and the results are combined, e. g. in a 2-from-3 manner. The recognition of persons may be used for pure identification or can be varied to a verification system. For both cases we have done a field test to show that this approach leads to a reliable person authentification system

Outdoor recognition at a distance by fusing gait and face

“…8. We see that states at the ends (states 1-3 and 18-20) and at the middle (9)(10)(11)(12) has the largest scatters, indicating that these gait stances carry the bulk of the discriminatory power. The mean stances for these states are shown in Fig.…”

“…Fusion can be done at three levels [39]: 1. The feature extraction level, where data from each sensor are: combined to form one feature vector [12,5]. 2.…”

Variability in echolocation call design of 26 Swiss bat species: consequences, limits and options for automated field identification with a synergetic pattern recognition approach

“…The classification of bat calls is achieved with an algorithm termed SC-MELT (Wagner et al 1995;Hogg & Talhami 1996;Dieckmann 1997 Apart from the raw classification rates we also calculated recognition rates with a filter criteria, which rejected classifications with maximum scalar product values smaller than 0.6 or with a difference to the next best scalar product of less than 0.2. We then tried to optimize the training base by picking from every species the calls from those random sets, which had achieved the highest classification rates.…”

The Concept of Complex Events as Suitable Means for Biometric System Implementation

“…Due to the development of biometrics and its machinesupported implementation, this method is nowadays widely used, whether applied by popular electronics or highly sophisticated devices and equipment [2], [5]. We have already analyzed biometric features and achieved results were published in [1].…”