3-In-1 Palm Recognition Powered By Computer Vision Technology
ZKTeco introduced the touchless palm recognition technology which was a breakthrough of touchless biometrics recognition, it was the first and the only recognition available. However, the previous technology was constrained by the angle tolerance and short recognition distance resulted in an imperfect user experience solution. After 5 years of R&D and the technological bloom of computer vision, in 2019 ZKTeco launched the next generation 3-in-1 Palm Recognition Technology.
The newest generation of palm recognition technology
is fully upgraded in all aspects in terms of recognition method, which combines
palm, palm print and palm vein recognition as one, with the help of the
delegated computer vision biometrics CPU, the whole recognition process can be finished
in 0.35 second. Moreover, the computer vision technology has greatly enhanced
the recognition performance, the angle tolerance is improved to as wide as +/-
60 degrees (roll axis), and the recognition distance can be up to 0.5 meters
upon the palm-size. Most importantly, the anti-spoof ability has reached a new
height of the industry, as the testing result has shown, all the testing
subjects including, fake HD photos, fake HD video, and fake palm model cannot
stand any chance to crack the system.
Recognition Process
When the palm close to the
camera, the camera will first function the palm recognition process to identify
whether this is a palm, if the nearing object is not a palm, it will stop the
further recognition process. If the nearing object is a palm, it will pass it
to the next step
Meanwhile, the infrared camera
will use the infrared light to observe the palm vein, which is normally
unobservable by the human eye, same as the palm print, it will recognize the
feature point of the palm vein and then cross-check with the database for its
availability
Technological Features
Anti-spoofing Technology With the
help of Computer Vision technology, the anti-spoof ability has been greatly
enhanced. The 3-in-1 combination of palm, palm print and palm vein sets an
extremely high bar for spoofing attacks to pass through. All attacks are guarded
throughout three layers as follows:
The latest algorithm contains the
palm recognition function, it can identify whether the object is in proper
“palm” shape, all the objects that are not in a proper “palm” shape will be
identified as non-palm object and will be refused to process to the further
recognition process.
After the 1st layer recognition, the palm shape object will go
for the second recognition process, the infrared camera will recognize the palm
print, as palm print is one of the unique features points of human being, and
is formed by hundreds of thousands of lines, accurate replication of palm print
is extremely hard to be done, and 90% of the fake palm will be identified and
rejected in this stage.
In this stage, the infrared camera will be activated. Under
normal sunlight, palm vein cannot be imaged, but under infrared light
(wavelength 700 – 900mm), the palm vein will become visible as the deoxygenated
hemoglobin in the blood exhibits stronger absorption characteristics than
moisture in other tissues and tissues under infrared light. Using a
near-infrared light source to illuminate the palm, the venous blood in the
shallow layer of the palm absorbs most of the light, while the body tissue such
as the skin absorbs light less and Reflects the light back. Through the imaging
of the image sensor, the venous blood vessels and other tissues are imaged with
a strong difference in brightness, so that the structural distribution of the
vein can be clearly distinguished. Hence the complication process to get a
clear image of the palm vein, and the vein image is extremely complex which is
involved with millions of vessels and some of the vessels are as tiny as a
hair, it is almost impossible to replicate a fake palm vein model to
pass the recognition process
Ultra-long Recognition Distance
With the help of the HD image sensor and HD and infrared camera technology
bloom in recent years, getting a clear palm, palm print and palm vein image in
the range of 10 – 60 cm is absolutely simple. With ZKTeco’s biometrics
processing unit, the whole recognition process can be finished in less than
0.35s, which is absolutely one of the nest in the industry
With the help of the HD image
sensor and HD and infrared camera technology bloom in recent years, getting a
clear palm, palm print and palm vein image in the range of 10 – 60 cm is
absolutely simple. With ZKTeco’s biometrics processing unit, the whole recognition
process can be finished in less than 0.35s, which is absolutely one of the nest
in the industry.
For more details, reach us via sales@zkteco.in