Biometric recognition for kids

Abstract

The idea of fusing multiple biometric modalities for the identification of an individual has received significant attention in the last two decades. However, this has been limited to recognizing adults only. With the quality of biometric hardware and sensors improving every year, it is surprising that this idea has not been explored for children within the age range of 2-5 years. In this project, we analyze whether we can use face, fingerprint and iris to identify children. In this semester, we collected the 2nd session of the database comprising fingerprint, face photo and iris sample for kids between age 2-4 years. We have used commercial-off-the-shelf tools (COTs) for iris and fingerprint to evaluate our database. Further, we have tried to improve the performance, through modality fusion