Indian researchers have created a unique database of 8,000 images of hand veins and palm prints using newly created hardware that captures four biometric data from each scanned hand.
According to a paper from the PES College of Engineering, from each hand, the multimodal device can record palmprint, dorsal vein, wrist vein, and palm vein. Contact is required.
The hardware used near-infrared light-emitting diodes to image the veins and a single-camera CMOS sensor to record them. The palm prints were illuminated using several white LEDs.
The researchers scanned 308 people to get 8,336 images of vein and palm prints from two hands each. Almost half of the participants were between 20 and 30 years old. About a third were between 15 and 20 years old. The others were between 30 and 80 years old. The creation of new biometric data sets has been a regular source of ethical and privacy concerns.
Classification accuracy with multimodal approach was 99.8% in k-nearest neighbor, 99% in random forest, 99.8% in support vector machine, 99.8% in neural network , 97.7% in gradient boosting and 99.8% in logistic regression.
Multimodal biometric systems to date have generally referred to systems that combine fingerprint or handprint with facial or iris recognition.
Fujitsu Laboratories in January 2021 demonstrated a multi-modal, contactless identity authentication retail approach. The system performed palm recognition and face verification with or without a mask.
A month later, the US Navy discussed a system it was using that collects biometric facial, fingerprint and iris identifiers.
precision | biometrics | biometric research | dataset | India | multimodal | palm footprints | research and development | vein recognition