19-01-2013, 11:59 AM
Comparison of Iris, Finger, Voice Recognition Techniques – A Biometric Perspective
Comparison of Iris,.pdf (Size: 319.46 KB / Downloads: 61)
Abstract
In the light of current lifestyle of humankind, there is a great need of high secure interfaces which apart from providing identification to the user, also enhances security. There are many biometric techniques and various new approaches that are being widely used in the fields of banking sector, security accesses, military, etc. But it is difficult to decide which of them is more feasible and secure. We tried to compare these Biometric Techniques and put forth the pros and cons of each of these methods while keeping a few major parameters as benchmarks. We believe this brief overview would help us to analyze the idea of the above approach, which would promote longevity and enable interoperability.
INTRODUCTION
There has been an enormous change in the use of science and security of which biometrics is one that is most widely discussed and experimented field. Biometrics has undergone drastic changes since its first inception as a Fingerprint recognizing method in China that dates back to 14th century Later on finger printing has become more standardized making it a gateway for other techniques like Finger, Iris, Voice Recognition etc. In the recent years, a number of recognition and authentication systems based on Biometric measurements have been proposed. There is no doubt in saying that Biometrics is going to be the most happening of all technologies in the field of Homeland Security.
SURVEY OF RELATED WORKS
There are many biometric techniques being used today and many new approaches are still in the early stages of development. Biometrics can, therefore, be grouped into two categories: those that are currently in use across a range of platforms and those still in limited use or still in the stage of development or some may still be in the minds of researchers. Here we present literature survey for some of the biometrics of the specified categories. This survey is based on the previous study and considering certain characteristics and performances of the modalities
PROBLEM STATEMENT AND MAIN CONTRIBUTION
Today safety and security has become a primary objective in various sectors. So, in adapting a certain biometric modality there is a need for a certain comparison scheme which enhances the usage of biometric methods and to reduce their error rate. Our research questions deals with comparison of various biometric methods, and also try to predict the future of Biometrics. We hypothesize that there have been many unanswered questions regarding the quality assessment in any one of these biometric technologies. Hence it is our aim to try and compare all those methods and provide our understanding for those who want to have a better perception based on factors like accuracy, dependency, safety, user friendly etc.
IRIS RECOGNITION: -
Iris Recognition is an automated ocular based automated method of that recognizes patterns matching techniques used for retina scanning. Common iris recognition systems contain five different stages: Iris acquisition, iris localization and segmentation, normalization, encoding and pattern matching. When someone participates in an iris- recognition system; his or her eyes are scanned to create iris codes, which are in fact binary representations of the image that are stored for security reasons to counter the malfeasance. A basic scheme is as follows where 3 stages are used to evaluate the identification of the user from a prespecified database entry.
RESULT
After collecting/analyzing the data which were extracted from the papers (2007-2012) that was studied, Observed six vital parameters that marks the accountability of the user to rely upon with, which provides a benchmark for these 3 biometric methods that are dominant in the field of advanced commercial applications. The realization of the parameters is as follows:
1. Accuracy: It depends on recognition rate and template matching rate. High matching rates results in better accuracy.
2. Dependability: It relies on FAR and FRR. FAR (False Acceptance rate) is the probability that the system incorrectly matches the input pattern to a non-matching template in the database. It measures the percent of invalid inputs that are incorrectly accepted, for example: a potential intruder. FRR (False Rejection Rate) is he probability that the system fails to detect a match between the input pattern and a matching template in the database. It measures the percent of valid inputs that are incorrectly rejected, for example: an authorized person.
CONCLUSION
According to the results obtained while taking the parameters into consideration, it can be said that Iris recognition technique dominates qualitatively over its biometric counterparts.
Fingerprint technology currently has 46% and 34% share in the biometric markets for the years 2007 and 2012 respectively. Although fingerprint has a lion’s share in the usage of biometrics, Fingerprint is gradually losing its hold. According to the International Biometric Group, the projected market study for the 2015 reveals that Iris is going to be the leading biometric modality with 19% of the total market share.