Iris is biological feature of a human. It is a unique structure of human which remains stable over a person lifetime. The iris is the annular region of the eye. The left and right irises of an individual can be treated as separate unique identifier. A sample human eye image (iris) is given in figure 1(d). The iris information can be collected by iris image. The accuracy of iris based recognition system is promising. Each iris is believed to be distinctive and even the irises of identical twins are also different.
The iris recognition system has become more users friendly and cost effective. The iris have a very low false accept rate as compared to other biometrics like finger print, face, hand geometry and voice. The iris image consists of the colored tissue surrounding the pupil. The iris recognition systems are known as real time, high confidence recognition of person identification. The iris has a misidentification rate of 1/1,200,000 and it can be used in high-security facilities. These systems are used in many applications like passports, activation security, and controlling access to restricted areas at airports, database access and computer login, access to building and homes, border crossings and other government programme. The iris recognition systems have following features:
1. Perform 1: n identification with no limitation on numbers.
2. The most robust biometric technology available in the market today never had a false acceptance.
3. Biometric templates once captured do not need to be enrolled again, iris stable throughout a human life.
Along with iris recognition technology, retina scan is perhaps the most accurate and reliable biometric technology. It is also among the most difficult to use and requires well-trained, and is perceived as being moderately to highly intrusive. The users have to be cooperative and patient to achieve a proper performance. Basically the retina, a thin nerve on the back of the eye, is the part of the eye which senses light and transmits impulses through the optic nerve to the brain. Blood vessels used for biometric identification are located along the neural retina which is the outermost of the retina’s four cell layers. Research has proven that the patterns of blood vessels on the back of the human eye were unique from person to person. It has even been proven that these patterns, even between identical twins, were indeed unique. This pattern also doesn’t change over the course of a lifetime. Retinal scanners require the user to place their eye into some sort of device and then ask the user to look at a particular spot so that the retina can be clearly imaged. This technology involves using a low-intensity infrared light source through an optical coupler to scan the unique patterns of the retina. The reflection of the vascular information is being recorded. Retina scanning works well in both modes, identification and verification. Additional advantages include the small template size and good operational speed. It involves 360° circular scan for taking 400 readings. Generally it is used for high-end security applications, primarily for physical access control. A sample human eye image (retina) is given in figure 1(e).
Various types of biometric technologies available today, voice identification and authentication solutions have a unique edge over much of the competition, because customers typically don’t need to purchase new hardware to implement the solutions. Most of the voice biometric solutions can be used through a typical telephone or microphone hooked up to the computer. In order to identify or authenticate users, most voice biometric solutions create a voice print of the user, a template of the person’s unique voice characteristics created when the user enrolls with the system. During enrollment the user has to select a pass phrase or repeat a sequence of numbers. The pass phrase should be in the length of 1 to 1.5 seconds. The problem with shorter pass phrases is that they have not enough data for identification. Longer pass phrases have too much information. The user has to repeat the pass phrase or the sequence of numbers several times. This makes the enrollment process lasting much longer than with other biometric technologies. All subsequent attempts to access the system require the user has to speak, so that their live voice sample may be compared against the pre-recorded template. A voice biometric sample is a numerical model of the sound, pattern and rhythm of an individual’s voice. A problem considering the voice is that people’s voices change over time along growth, or when someone has got a cold or other disease. Background noise can also be disturbing factor. The voice recognition systems have been currently used in various applications. Voice is a combination of physical and behavioral biometrics. The figure 1 (f) shows a sample speech signal. The features of person voice are based on the vocal tracts, mouth, nasal activities and lips movement that are used for synthesis of sound. These physical characteristics of human speech are invariant for individuals. The behavioral part of the speech of person changes over time due to age, medical conditions, and emotional state. The speaker dependent voice recognition systems are text dependent; and the speaker independent systems are what he or she speaks. The speaker dependent voice recognition system is more difficult to design but provides more protection. The speech recognition is most important research area in the today’s world. There are various speech recognition approaches; among those are the acoustics phonetic pattern comparisons and automatic speech recognition approach. The performance of speech recognition system depends on various factors some of them are speaker variation, ambient noise, and variation in the tone of the same speaker, sensitivity of phonetic input systems, distance and regular variations. The speaker recognition is most appropriate in phone based applications, the entertainment TV channels. Banks are starting to use this technology, instead of dialing in a pin number you would speak and the computer would recognize your voice. It has misidentification rate 1/30 and can be used in low security facilities. Voice
Signature recognition biometric systems are used for access control, banking, government offices and entertainment applications, smart cards, PIN and other security purposes.
Signature verification is the process used to recognize an individual’s hand-written signature. Dynamic signature verification uses behavioral biometrics of a hand written signature to confirm the identity of a person. This can be achieved by analyzing the shape, speed, stroke, pen pressure and timing information during the act of signing. On the other hand there is the simple signature comparison which only takes into account what the signature looks like. So with dynamic signature verification, it is not the shape or look of the signature that is meaningful, it is the changes in speed, pressure and timing that occur during the act of signing, thus making it virtually impossible to duplicate those features. Devices which enable dynamic signature verification store the behavioral factors and the captured signature image itself for future comparison in their database. These devices account changes in one’s signature over time by recording the time and the dynamic features each time a person uses the system. The major difficulty with this technology is to differentiate between the consistent parts of a signature; these are the characteristics of the static image, and the behavioral parts of a signature, which vary with each signing. Comparing many signatures made by one individual reveals the fact that an individual’s signature is never entirely the same and can vary substantially over an individual’s lifetime. Allowing these variations in the system, while providing the best protection against forgery is a big problem faced by this biometric technology. Functions are provided to capture that handwriting, extract the relevant features, and compare two different samples. It has misidentification ratel/100 and can be used in low security facilities. The financial industry sometimes uses signature verification for money transactions. The Manhattan Bank was the first bank to test such an approach by using a biometric signature application for their money transaction system. The figure l (g) shows a sample signature.
The biometric systems such as fingerprint, hand geometry, face, iris, retina, and Signature have compared based upon factors such as accuracy, ease of use and user acceptance. These factors are different for each biometric type. These can be measured in High (H), Medium (M) and Low (L) . Table 1 compares the biometric systems based on different factors.