Contactless Palmprint Recognition for Children

Effective distribution of nutritional and healthcare aid for children, particularly infants and toddlers, in the world's least developed and most impoverished countries, is a major problem due to lack of reliable identification documents. We present a mobile-based contactless palmprint recognition system, Child Palm-ID, which meets the requirements of usability, cost, and accuracy for child recognition. On a contactless child palmprint database, Child-PalmDB1, with 1,020 unique palms (age range of 6 mos. to 48 mos.), Child Palm-ID achieves a TAR=94.8% at FAR=0.1 %. Child Palm-ID is also able to recognize adults, achieving a TAR=99.5% on the CASIA contactless palmprint database and a TAR=100% on the COEP contactless adult palmprint database, both at FAR=0.1 %. For child palmprint images captured at an interval of five months with differences in standoff distance, illumination and motion blur, the TAR drops to 80.5% at FAR=0.1 %. This indicates that more research opportunities remain in contactless child palmprint recognition.