ERROR CORRECTION ON IRIS BIOMETRIC TEMPLATE USING REED SOLOMON CODES
Pin number or password that is used for authentication can be easily attacked. This limitation triggered the utilization of biometric for secured transactions. Biometrics is unique to each individual and is reliable. Among the types of biometrics being used currently, iris is the most accurate and it remains stable throughout a person’s life. However the major challenge on iris and other biometrics for authentication is the intra user variability in the acquired identifiers. Iris of the same person captured at different time may differ due to the signal noise of the iris camera. Traditional cryptography method is unable to encrypt and store biometric template, then perform the matching directly. Minor changes in the bits of the feature set extracted from the iris may lead to a huge difference in the results of the encrypted feature. In our approach, a cancellable iris biometric template using iris biometric and passwords is being proposed. Error Correction Code, ECC is introduced to reduce the variability and noise of the iris data. Experimental results show that this approach can assure a higher security with a low false rejection or false acceptance rate. The successful iris recognition rate using this approach is up to 97%.
History has proven that human can remember only short password, most of the user even tend to choose password that can be easily guessed using dictionary or brute force search. This limitation has triggered the utilization of biometric to produce strong cryptographic key. Biometrics is unique to each individual and it is reliable. For years, securities to the world are mostly based on what one knows such as password, PIN, or a security question such as mother’s maiden name. This security feature is easily forgotten, stolen, shared and cracked. Biometrics is a measurement of a person to their biological or physical characteristics to determine the human identity of (who you are?). There are different types of biometric technologies available today which are fingerprints, face, iris/retina, hand geometry, signature, DNA, keystroke and tongue. Biometrics is used to enhance the privacy and security weaknesses exist in the current security technology such as simple password or PIN authentication. Although biometrics is unique among all individuals, it is not possible to used biometrics as a direct cryptography key for the system due to the difference bits occur in the template during every authentication. Biometric images or templates are variable by nature which means each new biometric sample is always different. Noises and error may occur in the captured image due to burst or background error and hence the generated template is different during every authentication. There is also awareness concerning the privacy and the security of personal information due to the storage of the biometric templates. The loss or compromise of biometric templates may end up to unusable biometrics. Human biometrics is impossible to change or do modification if the image template has been stolen or compromised. To solve the problem, two questions below have to be solved.
Free download research paper