Reviewed by Lexie CornerMar 10 2025
Researchers from Osaka Metropolitan University’s Center for Health Science Innovation used a hyperspectral camera and AI to capture detailed images of people's palms. This approach enabled accurate identification based on unique blood vessel patterns, highlighting potential applications in secure biometric authentication and health monitoring systems.
Through a hyperspectral camera and AI, differences in the palm can provide highly personalized security. Image Credit: Osaka Metropolitan University
Hyperspectral imaging is a technique that uses subtle color variations to identify an object's properties and state. Unlike a standard camera, which uses red, green, and blue to create images, a hyperspectral camera captures over 100 images across the visible to near-infrared light range in a single shot. This allows information that is invisible to the human eye to be obtained.
In the case of palm images, the hemoglobin in red blood cells absorbs light, revealing the condition of blood vessels in the palm. Since blood vessel patterns differ from person to person, individuals can be distinguished based on these unique patterns.
Additionally, vein patterns are less visible on the skin's surface compared to fingerprints or facial features, making this bioinformation highly secure due to its difficulty to capture.
To test this, Dr. Suzuki developed an AI-based image recognition technique that identifies biometric data regardless of orientation or position. By stacking images in order of wavelength and aligning them with coordinates obtained through AI, the researcher was able to create more precise, smaller, and information-rich images than traditional methods.
It was possible to distinguish between the subjects. Furthermore, the accuracy of the developed method was verified, and a high discrimination accuracy was confirmed. Biometric authentication using hyperspectral images provides remarkably high security through the palm of a hand, thus, it could even be used as keys to a house. If the capability to read the state of health from the hyperspectral imaging of the palm becomes possible, a daily health management system could be developed with health data obtained through biometric unlocking.
Takashi Suzuki, Associate Professor, Osaka Metropolitan University
Journal Reference:
Suzuki, T. et al. (2024) Personal identification using a cross-sectional hyperspectral image of a hand. Journal of Biomedical Optics. doi.org/10.1117/1.jbo.30.2.023514.