Precision can help you craft & successfully execute your IoT initiative. Discover how in our guide featuring exclusive research from
Biometric technologies protect an organization through several identity verification techniques such as fingerprint, iris and face biometrics and ensure organizations are safe from data theft and impersonations.
Precision enables several leading banks, private enterprises and government organizations with biometric security systems to protect the organization and its consumers’ data & financial transactions from risks and improves efficiency while enhancing the organization’s performance.
With Precision’s biometric technology, the process of identification is simplified, accurate, value-adding and cost effective. Specifically designed for particular industries, it focuses on protecting citizens and customers from all forms of identity theft.
Precision’s Biometric R&D continues to develop solutions to create a blend of security and convenience across several business verticals and scenarios.
The current technology that uses fingerprint Biometrics can be categorized into two major areas: Image Acquisition Technologies & Image Processing Technologies
Image Acquisition Technologies include sensors utilized to deliver the highest quality image possible for Precision Biometrics.
Forms of IAT suitable for fingerprint scanners are:
Optical Sensors: Optical fingerprint imaging involves capturing a digital image of the fingerprint using visible light. In simple terms, this type of sensor is, just a specialized digital camera. Traditionally, this type of sensor has had some limitations in imaging unclean fingers. In addition, it was relatively easy to circumvent this sensor. However, Precision’s advanced sensors address this issue to a great extent.
Capacitive Sensors: Capacitive Sensors use the principles of Capacitance to form an image of the fingerprint patterns on the dermal layer of skin. Each sensor pixel is used to measure the capacitance at that point of the array. The capacitance varies between the ridges and valleys of the fingerprint due to the fact that the volume between the dermal layer and sensing element in valleys contains an air gap.The measured capacitance values are then used to distinguish between fingerprint ridges and valleys.
RF Sensors: RF sensors make use of the principles of medical ultrasonography to create visual images of the fingerprint. The sound waves are generated using piezoelectric transducers and reflected energy is also measured using piezoelectric materials. Since the dermal skin layer exhibits the same characteristic pattern of the fingerprint, unlike optical sensors, RF sensors can work well even if finger skin is not very clean.
Thermal Sensors: Thermal Sensors are made out of pyroelectric materials, which change their electrical property according to the temperature. A pixel array is formed using these materials, which sense the heat at all points of the finger. The heat at the ridge will be that of the body temperature, with the same at the valley will be the atmospheric temperature of the air. The temperature difference is used to differentiate between the peak and the valley of the fingerprint. This is measured at very high resolution as each sensor pixel is as tiny as 50 micron X 50 micron. A 3D image of the fingerprint is generated using as many as 100,000 sensing points.
Fingerprints are made up of lines known as ridges (peaks) and valleys that bifurcate and end to form several unique characteristics. These characteristics, such as Ridge Island and Ridge Endings, are commonly termed as Minutiae Points and the patterns they form are unique with every fingerprint.
To identify and extract these minutiae patterns from each fingerprint, the digital image undergoes a set of image processing techniques. This process can classified into the following phases:
As it may not be possible for people to keep all the fingers clean all the time, so may be the consequent effect on the image of the fingerprint.
Whatever be the image acquisition technology, the contrast and completeness of the digital image generated by the sensor, still requires enhancement, to get accurate results.
Removing blurs, adding mixing pixels, improving the image contrast etc. are archived by adapting spatial methods and frequency methods for image enhancement and subjecting the image into transformations like Fourier and Gaussian.
This enhanced image is a gray scale image, and all the pixels forming this image have an intensity value ranging between 0 and 255.
Various parameters like average image pixel intensity, ridge pixels’ intensity distribution, valley pixels’ intensity distribution and like parameters are analyzed to arrive at a threshold intensity value.
Physically a fingerprint ridge (or a valley) will be around 300 – 500 microns. Since the image acquisition is carried out at 50 micron, the digital image of a ridge line (or a valley line) will be formed by around 6 – 10 pixels.
The middle pixel of this ridge line maintained at intensity 255 and the rest of the pixel’s intensity are changed to 0, thereby thinning the ridge line width to a single pixel line.
The thinned image is then analyzed to spot minutiae points. An eight pixel square is formed around the ridge pixel and this pixel square is moved along the ridge line.
Any ridge pixel having more (or less) than two of the eight pixels in the square with intensity value other than 255 is noted as a minutiae point.
The location (x, y coordinates) of all these minutiae points, (along with angle theta, in case it is a bifurcation minutiae) stored in an encrypted file format. This is called the minutiae template file.
A fingerprint may have around 50 – 80 minutiae points and the minutiae template will be around 800 bytes as against an 80 kilobyte image. This makes it so easy to transmit it through even thin bandwidths for comparisons.