Soft biometric fusion for subject recognition at a distance

There is societal need for techniques to identify subjects at a distance and when conventional biometrics are obscured, for example in fighting crime. Soft biometrics have this capability and include a subject's height, weight, skin colour and gender. Although the distinctiveness of soft biometric features is intuitively less than that of traditional biometric features, numerous experiments have demonstrated that the desired recognition accuracy can be achieved by using multiple soft biometric features. This paper will propose state-of-the-art multimodal biometric fusion techniques to improve recognition performance of soft biometrics. The key contribution of this paper is the analysis of the influence of distance on soft biometric traits and an exploration of the potency of recognition using fusion at varying distances. A new soft biometric database, containing images of the human face, body and clothing taken at three different distances, was created and used to obtain face, body and clothing attributes. This new database was constructed to explore the suitability of each modality at a distance: intuitively, the face is suitable for near field identification, and the body becomes the optimal choice when the subject is further away. The new dataset is used to explore the potential of face, body and clothing for human recognition using fusion. We present a novel fusion technique at score and rank level that improves identification performance. A novel joint density distribution-based rank-score fusion is also proposed to combine rank and score information. Analysis using the new soft biometric database demonstrates that recognition performance is significantly improved by using the new methods over single modalities at different distances