Authentication Tools

	Fingerprint Recognition
	Face Recognition
	Iris Recognition
	Hand Scan
	Voice Recognition

Fingerprint biometrics

Fingerprint biometrics is probably the most common form of biometrics available today. Fingerprints, when scanned electronically, provide greater details and hence higher level of accuracy can be achieved over manual systems. The fingerprint's strength is its acceptance, convenience and reliability. It takes little time and effort using a fingerprint identification device to have his or her fingerprint scanned. Studies have also found that using fingerprints as an identification source is the least intrusive of all biometric techniques. 

Verification of fingerprints is also fast and reliable. Users experience fewer errors in matching when they use fingerprints as against many other biometric methods. In addition, a fingerprint identification device requires very little space on a desktop or in a machine. Several companies have produced capture units smaller than a deck of cards. Finger-scan technology is thus the most prominent biometric authentication technology, used by millions of people worldwide. Used for decades in forensic applications, finger-scan technology is steadily gaining acceptance in fields as varied as physical access, network security, service access, e-commerce and retail.

Face recognition

Facial scan technology is an increasingly prominent biometric authentication technology, one well suited for a number of applications in which other biometric technologies are simply unusable. Face recognition technology involves analyzing certain facial characteristics, storing them in a database and using them to identify users accessing systems. There are various recognition methods that emphasize identification based on the areas of the face that don’t change, including: upper sections of eye sockets, area surrounding the cheek bones and the sides of the mouth.

Making use of distinctive features or characteristics of the human face, often irrespective of facial hair or glasses, facial scan is deployed in fields as varied as physical access, surveillance, PC access, and ATM access. Authentication process involves the user entering some identifying information such as a login name or pin, having a snapshot taken in front of the camera and then being verified. You may have seen facial recognition products currently implemented at airports and border crossings. It also has the ability to track moving faces. There are four primary methods used to identify and verify users. They include eigenfaces, feature analysis, neural network and automatic face processing. Eigenfaces, which means roughly "one’s own face", is a MIT patented technology, which utilizes two dimensional grayscale images representing distinctive characteristics of a facial image. Neural Network analyses features from both images, the enrollment and verification image and determines if there is a match using an algorithm. Automatic Facial Processing (AFP) uses distances and distance ratios between certain features of the face, namely eyes, end of nose and corner of mouth. It is not as robust as Eigenfaces, but would be more effective in a dimly lit situation. Face recognition technology works well with most of the shelf PC cameras, generally requiring 320 x 240 resolution at 3-5 frames per second. Obviously, better resolution cameras with higher frames per second will yield better quality images.

Iris recognition

Iris biometrics is exceptionally accurate, especially in environments where the fingerprints are worn out due to hard manual labor. Iris technology is relatively more expensive to use and does take-up slightly more time for the enrollment and authentication process. Iris scanners are typically multi-purpose and incorporate regular video capabilities with the scanner. Iris biometric devices are more accurate than fingerprint because an iris has more characteristics to identify and match than those found on the finger. These type of devices have come a long way in recent years allowing the individual to be scanned even through their glasses or contacts. The error rate for the typical iris scanner is about one in two million attempts, which further demonstrates the reliability of this technology. Two drawbacks to this device however are, that it has difficulty in reading images of people who are blind or have cataracts. 

There are several industries, which are interested in this type of technology, particularly banking & Finance. Banks are incorporating Iris Scanning systems into their ATMs. Some prisons are also using this technology today to identify inmates and guards.

Hand Scan

Hand-scan is a relatively accurate technology, but does not draw as rich a data set as finger, face, or iris. A decent measure of the distinctiveness of a biometric technology is its ability to perform one-to-many searches - that is, the ability to identify a user without the user first claiming an identity. Hand-scan does not perform one-to-many identification, as similarities between hands are not uncommon. The submission of the biometric is straightforward, and with proper training can be done with little misplacement. The template size of a hand scan is up to 9 bytes which is extremely small compared to most other biometric technologies. By contrast, finger scan biometric requires 250-1000 bytes and voice scan biometric commonly requires 1500-3000 bytes. This facilitates storage of a large number of templates in a standalone device. It also facilitates card-based storage, as even magstripe cards have ample room for 9 byte samples. 

Voice recognition

Voice recognition is "the technology by which sounds, words or phrases spoken by humans are converted into electrical signals, and these signals are transformed into coding patterns to which meaning has been assigned" The most common approaches to voice recognition can be divided into two classes: "template matching" and "feature analysis". Template matching in voice recognition is the simplest technique and has the highest accuracy when used properly, but it also suffers from the most limitations. As with any approach to voice recognition, the first step is for the user to speak a word or phrase into a microphone, the electrical signal from the microphone is digitized by an "analog-to-digital (A/D) converter", and is stored in memory. To determine the "meaning" of this voice input, the computer attempts to match the input with a digitized voice sample, or template, that has a known meaning.

Most voice recognition systems are discrete word systems, and these are easiest to implement. For this type of system, the speaker must pause between words. This is fine for situations where the user is required to give only one word responses or commands, but is very unnatural for multiple word inputs. In a connected word voice recognition system, the user is allowed to speak in multiple word phrases, but he or she must still be careful to articulate each word and not slur at the end of one word into the beginning of the next word. Totally natural, continuous speech includes a great deal of "co articulation", where adjacent words run together without pauses or any other apparent division between words. A speech recognition system that handles continuous speech is the most difficult to implement. Voice recognition uses a neural net to "learn" to recognize your voice. As you speak, the voice recognition software remembers the way you say each word. This customization allows voice recognition, even though everyone speaks with varying accents and inflection.