Importance of biometric user identification is increasing everyday. One of the most promising techniques is the one based on the human iris.
The possibility that the human iris might be used as a kind of optical fingerprint for personal identification was suggested originally by ophthalmologists. Some properties of the human iris that enhance its suitability for use in automatic identification include: 1) its inherent isolation and protection from the external environment, being an internal organ of the eye, behind the cornea and the aqueous humor; 2) the impossibility of surgically modifying it without high risk of damaging the user’s vision; and 3) its physiological response to light, which provides the detection of a dead or plastic iris, avoiding this kind of counterfeiting.
The biometric identification problem can be categorized into two types:
Recognition (or identification): recognition refers to the problem of establishing a user’s identity.
Verification (or authentication): verification refers to the problem of confirming or denying a user’s claimed identity.
We can solve these problems going through differente phases:
Image acquisition and pre-processing: being the cornea transparent, the user’s samples are captured using a high resolution photo camera each isolated iris sample which allows a suitable extraction of its features. performed. Then, the image of the eye is converted to grayscale and its histogram is stretched. Then, throughout a griding process, the centre of the iris, as well as the outer boundary is detected taking advantage of the circular structure of the latter. Once detected, the outer bounds of the iris, everything in the image outside it is suppressed, and the same process is performed in order to find the inner boundary. The points inside this last border are also suppressed. In the last step of the pre-processing block, the dimensions of the irises in the images will be scaled to have the same constant diameter, regardless of the original size of the images.
Feature Extraction: in our biometric system based on the human iris pattern, the first step of the feature extraction block is to get a data set from. In this way, we consider the centroid of the detected pupil is chosen as the reference point for obtaining this data set. We introduce an algorithm for extracting unique features from iris signatures and representing these features using a discrete dyadic wavelet transform. When a signal includes important structures that belong to different scales, it is often helpful to reorganize the signal information into a set of “detail components” of varying size. Finally, in order to obtain a robust representation in noisy environments, and to reduce the amount of computations required, only a reduced number of resolutions levels are used.
Classification and verification: all the features obtained should enter a comparison process to determine the user whose iris photograph was taken. The following methods have been used: The euclidean distance, considered the most common technique, performs its measurements with the dimension of the feature vector, the ith component of the sample feature vector, and the ith component of the template feature vector. The (binary) Hamming distance does not measure the difference between the components of feature vectors, but the number of components that differ in value. A distance directly related with the zero-crossing representation of a 1-D signal that is computed using only the zero-crossing points. The overall dissimilarity value of the unknown object and the candidate model over the resolution interval [K, MI] will be the average of the dissimilarity functions calculated at each resolution level in this interval.
- Biometric access control physical or logical
- Biometric time and attendance
- Wireless biometrics for high end security and providing safer transactions from wireless devices like smartphones, PDAs, etc.