Soft biometric traits like gender, age, height, weight, ethnicity, and eye color cannot provide reliable user recognition because they are not distinctive and permanent. However, such ancillary information can complement the identity information provided by the primary biometric traits (face, fingerprint, hand-geometry, iris, etc.). This paper describes a hybrid biometric system that uses face and fingerprint as the primary characteristics and gender, ethnicity, and height as the soft characteristics. We have studied the effect of the soft biometric traits on the recognition performance of unimodal face and fingerprint recognition systems and a multimodal system that uses both the primary traits. Experiments conducted on a database of 263 users show that the recognition performance of the primary biometric system can be improved significantly by making use of soft biometric information. The results also indicate that such a performance improvement can be achieved only if the soft b...
Anil K. Jain, Karthik Nandakumar, Xiaoguang Lu, Un