Documente Academic
Documente Profesional
Documente Cultură
Rajiv (AP/CSE)
BATCH NO 16
Gali Sivaditya
(12608104012)
Gangadharan.V (12608104013)
OBJECTIVE
Our first approximation was to perform the biometric acquisition by means of a mobile phone as per the PC
Many commercial and research efforts have recently focused on this subject.
However, in spite of the great amount of particular applications that can be found, the cost of changing or modifying biometric platforms, the lack of normalization in capture-device technology, and communication protocols, as well as social-acceptance drawbacks, are all barriers to the popularization of biometric recognition.
The dominant approach on current control access is via password or PIN, but its weaknesses are the most clearly documented: if it is easy to remember, it is usually easy to guess and hack into, but if it is difficult to attack, it is usually difficult to remember; hence, a lot of people write them down and never change them. The problem with tokens is that they authenticate their presence, but not the carrier; they can be easily forgotten, lost, or stolen, and, as it happens with the credit cards, can be fraudulently duplicated.
As far as the knowledge, none of the work has approached the biometric recognition in a mobile environment via the web. Second, we have proved that the standard solutions to approach the problem in pc platforms, using java applets, ActiveX controls, JavaScript, or flash technology, do not work under mobile platforms. Therefore, a new alternative is needed.
The main contribution of our proposal is that this capture, and later recognition, can be performed during a standard web session, using the same architecture that is used in a personal computer (PC). The main characteristics of our proposal with regard to the state of the art are Simplicity, Low Cost, Multiplatform, and Secure. A lot of works/applications can be found that focus on the use of biometry with mobile devices; however, as far, none of them show a similar system to the one in this paper: a general proposal to capture biometrics by means of a mobile phone during a standard web session. This capture can only be stored in the server or used with remote (i.e., web service) or local (i.e., mobile data or application) restricted access.
We perform Client Registration from our mobile end to connect it to our server which in turn creates account id and user id for the respective client.
The Score-normalization is to improve the system performance or to use a universal decision threshold. From the comparison of the score with a decision threshold, this determines whether the user is accepted or rejected and is, thus, granted or denied access to the system or protected services and transmits the output back to the client.
The basic principle of the Viola-Jones algorithm is to scan a sub-window capable of detecting faces across a given input image. Here we rescale the detector instead of the input image and run the detector many times through the image each time with a different size. Here a devised scale invariant detector is there and that requires the same number of calculations whatever the size. This detector is constructed using a so-called integral image.
The first step of the Viola-Jones face detection algorithm is to turn the input image into an integral image. In order to find these features Viola-Jones use a modified version of the AdaBoost algorithm. The cascaded classifier is composed of stages each containing a strong classifier. The job of each stage is to determine whether a given sub-window is definitely not a face or maybe a face. When a sub-window is classified to be a non-face by a given stage it is immediately discarded.
TESTING
RESPONSE TIME TEST The response time of the biometric comparison (search) measured from the time the biometric is scanned or captured to the time the comparison result is returned (including a validation step, if required) is an important consideration when designing or selecting a biometric system. If the response time of the system too high, the system may be of no use.
TIME TAKEN TO COMPARE THE TIME TAKEN TO COMPARE THE IMAGES IMAGES AND PRODUCE THE AND PRODUCE THE RESULT8 RESULT
5-7 seconds
1-2 seconds
RESULT
YES
YES
COMPATIBILITY TESTING
Testing technique that validates how well software performs in a particular hardware/ software/ operating system/ network environment. It is performed by the testing teams.
VERSION (NAME) YES/NO
V1.0 Beta
v1.5 Cupcake v1.6 Donut v2.0/2.1 Eclair v2.2.x Froyo
NO
NO NO NO YES
v2.3.x Gingerbread
v3.x Honeycomb v4.x Ice Cream Sandwich
YES
YES YES
In this paper, the problem of using biometric user authentication during a standard web session when a mobile phone is used has been successfully approached. We have focused on the technological problem of capturing the biometric with the mobile phone, sending it to the web server, and, after user authentication, allowing or rejecting the users continuation with the web session in the same way this had been performed using password authentication.
FUTURE ENHANCEMENT
The project (TOWARDS MOBILE AND BIOMETRIC AUTHENTICATION FOR CONTROLLED WEB SERVICES) is developed considering time, material and money. Since our objective of the project is successfully completed. This system provides efficiency in many ways. All the complications concerned with this project are successfully solved. Every application has its own merits and demerits. The project has covered almost all the requirements.
Further requirements and improvements can easily be done since the coding is mainly structured or modular in nature. Changing the existing modules or adding new module can append improvements.
This project is developed solely on the current technologies in the market and can also adapt to the future technologies and it will ply root steps to the future projects.
THANK YOU