Statistical Feature Analysis of Human Footprint for Personal Identification Using BigML and IBM Watson Analytics

Personal identification based on biometrics is an essential element of security systems with many challenges that would have the day-to-day life. This paper presents a deep analytical study on distinguishing features of human footprint images. The EPSON Stylus CS5500 scanner has been used for taking footprint images collected from 220 volunteers. BigML and IBM Watson Analytics processes footprint dataset. Set of 100 fuzzy rules has been exploited for the predictive analysis of the human footprint for personal identification. Footprint dataset of 440 images has been verified for data quality of 90% and predictability of 97%. GPUs have been applied to speed up the performance.