Path: EDN Asia >> Design Ideas >> Industrial/Mil/Aero >> Finger vein identification lowers cost for biometric system
Industrial/Mil/Aero Share print

Finger vein identification lowers cost for biometric system

17 Sep 2013  | Tan Pin Yang, Lau Wei Cheang, Bakhtiar Affendi bin Rosdi

Share this page with your friends

A state machine is used to program the architecture of the system because there are a lot of state overlaps for the enrolment mode and identification mode. Besides that, whenever there is an extra feature the programmer wishes to add into the program, the state machine easily scales to more states to add the extra feature without changing the overall architecture of the system. Figure 3 shows one of the state block diagrams of the state machine of this system.

state block diagram

Figure 3: A state block diagram in the state machine of the system. The state machine can scale to add new states without changing the overall architecture. (Click here to see larger image.)


The finger vein recognition algorithm (figure 4) is implemented using Labview because it is able to provide a simple approach to reduce design time. It provides most of the image processing library, such as image type conversion Virtual Instrument (VI), image Fast Fourier Transform (FFT), and Inverse Fast Fourier Transform (IFFT) VI.

The working principal is that near infrared light can penetrate the finger where it is absorbed by the haemoglobin of the blood in our veins. The vein will seem darker as compare to the muscle of the finger. Hence, a camera is modified to capture the infrared finger vein image. A casing which consists of camera and infrared is built to let the user to put their finger and acquire the image (figure 1).

The acquired image is grey-scaled by using the Image Casting VI. In case the acquired image is slightly rotated, an angle correction algorithm is implemented to correct the angle of the image. Hence, the image rotation VI in the vision development module and some custom VIs are adopted in our algorithm to correct the angle of the image. The algorithm ensures that the image is in the correct position every time it is taken. It further increases the system's stability and accuracy.

figure vein recognition algorithm

Figure 4: The figure vein recognition algorithm. The block diagram above shows the process of acquiring and processing the image to matching it with information in the database.


To optimise the accuracy of the system, the vein patterns have to be in high contrast with respect to the muscle. Hence, the resized image is enhanced by using Modified Gaussian Filter (MGF) algorithm. By using this algorithm, the veins pattern will appear in black in colour whereas the muscles appear white.

Before undergoing Band-Limited Phase Only Correlation (BLPOC) matching algorithms, the phase of the image is extracted using the phase extraction algorithm. The Image FFT VI is used to transform the enhanced image into a complex image so that the phase of the complex image can be used for matching algorithm.

The tester is treated as genuine if the matching score is greater than the threshold score but is treated as an imposter if the matching score is less than the threshold.

A feedback control is used to assist the system in adjusting the intensity of infrared LED so that the acquired image is in the best contrast. This automated control system is implemented using an FPGA and external circuitry. In a fixed intensity implementation, the vein image bursts [in a white-out (over-exposure)] for female fingers whose skin is thin or is too dark [due to under-exposure] for fingers with thicker skin. On the contrary, the feedback allows the system to compensate for skin thickness produce sharp and clear vein images despite subject variations. The feedback system tremendously increases the enrolment rate.


 First Page Previous Page 1 • 2 • 3 Next Page Last Page


Want to more of this to be delivered to you for FREE?

Subscribe to EDN Asia alerts and receive the latest design ideas and product news in your inbox.

Got to make sure you're not a robot. Please enter the code displayed on the right.

Time to activate your subscription - it's easy!

We have sent an activate request to your registerd e-email. Simply click on the link to activate your subscription.

We're doing this to protect your privacy and ensure you successfully receive your e-mail alerts.


Add New Comment
Visitor (To avoid code verification, simply login or register with us. It is fast and free!)
*Verify code:
Tech Impact

Regional Roundup
Control this smart glass with the blink of an eye
K-Glass 2 detects users' eye movements to point the cursor to recognise computer icons or objects in the Internet, and uses winks for commands. The researchers call this interface the "i-Mouse."

GlobalFoundries extends grants to Singapore students
ARM, Tencent Games team up to improve mobile gaming


News | Products | Design Features | Regional Roundup | Tech Impact