
If you thought face recognition technology was bad, researchers say they can identify you from the veins on the backs of your hands. The pattern of veins on the back of a hand is as unique as a fingerprint and can thus be used to identify them.
Researcher Syed W. Shah, at the School of Computer Science and Engineering, University of New South Wales in Australia used images of 35 volunteers, taking 17,500 photos of the back of their hands, using Intel RealSense D415 camera. This camera is sensitive to infrared light, so it can differentiate blood in veins from body tissue. It can detect how far away an object is and the stereo lenses, help to isolate the hand from the background.
The pattern of veins in each image was extracted and further processed for clarity. This pattern was then used to train a neural network to connect a pattern to a particular person. The resulting neural network model was used to identify the volunteers with an accuracy of 99.8 per cent. The model was also used to test its ability to detect vein patterns that weren’t included in the original data set. Four new subjects were identified as unknown with 96 per cent accuracy.
Existing biometric tests are susceptible to hacking and this technique is more robust. Fingerprints can be collected from smooth surfaces and used to trick sensors, while face recognition can sometimes be fooled with a photo. Contact lenses could be used to confound iris based mechanisms, The team also found that vein detection works reliably on people of all ethnicities, which has been an issue for some biometric tests.
Vein patterns lie underneath the skin and do not leave any imprint on surfaces and they are not available on social media. Hence vein patterns are considered to be more reliable. Researchers believe the technology can be adapted to run on smartphones. Apple’s iPhone 12 already has a built-in lidar scanner that can detect range, and many cameras are able to detect at least some infrared light. This could eventually work with CCTV cameras.
Reference:
Categories: Blog
Leave a Reply