Implementation of multimodal neonatal identification using Raspberry Pi 2

Abduction, swapping and mix-ups are the unfortunate events that could happen to newborn while in hospital premises and medical personnel are finding it difficult to curb this unfortunate incident. Traditional methods like birth ID bracelets and offline footprint recognition systems have their own drawbacks. Hence, a neonatalonline personal authentication system is proposed for this issue based on multimodal biometric system wherein footprint and palm print of neonatal is used for recognition. This concept is further enhanced by developing a prototype to be implemented on a Raspberry Pi 2 (a single board computer). In this paper, SIFT feature extraction, RANSAC algorithm for identification of matched interest points of palm print and footprint biometrics using OpenCV on Raspberry pi is implemented. The Raspberry Pi is a quad core ARM Cortex A7 application processor, System on chip (SoC) denoted as Broadcom BCM2836. It enhances performance, consumes less power, and reduces overall system cost and size. The Raspberry Pi is been controlled by a modified version of Debian Linux OS optimized for ARM architecture. The image recognition is performed using open source OpenCV-3.1.0 in Linux platform using CMake, g⁺⁺, makefile. Thereby the proposed system improves the security system in hospitals / birth centers and provides a low cost solution to the newborn swapping rather than the expensive DNA and HLA(Human Leukocyte Antigen)typing procedures. The efficiency(97.2%) is high when multimodality is used than unimodality. This paper elucidates the research works carried on hardware as a biometric module to enhance the performance of a standalone device.