Personal authentication using 3 d finger geometry (synopsis)
Download as DOC, PDF1 like1,173 views
The document proposes a 3D finger geometry authentication system as an improvement over existing hand geometry authentication methods. It captures 3D information using a low-cost depth sensor to limit constraints on hand placement. It extracts 3D geometry points from the finger and uses those as features for authentication, achieving similar accuracy to other methods but with greater convenience. It segments the finger, finds boundary points, enlarges the image, and extracts geometry points along circles projected inward from the boundary to generate the feature vector for matching. Preliminary results found the proposed system comparable to state-of-the-art hand geometry recognition.
![of silhouette points.
The authentication accuracy of the system for a database of 53
person was about 2% FAR and 1.5% FRR. The major limitation of the
above approaches is their obtrusiveness imposed by the use of pegs,
which constrain the positioning
and posture of the hand. Moreover, correct placement of the hand
requires some training, and presents difficulties for specific user
groups such as young children and elderly. Therefore, several
researchers have proposed to remove the requirement for
pegs, and use a document scanner or back-lit display for acquisition of
hand images. In a feature-based approach is used and an FRR close
to 3% was achieved for an FAR of 1% on a database of 70 people. Also
extracts hand features from hand silhouettes and employees a
hierarchical authentication scheme. For a database of 22 people FRR at
12% for FAR at 2.22% is reported. Finally in [6], implicit polynomials
are fitted on hand contours and geometric invariants are subsequently
computed from these polynomials. The invariants are then combined
with geometric hand features to perform matching and an FRR of 1%
for an FAR of 1% on a small database (45 images) is reported.
The problems are:
o Easily traceable by intruders
o Low reliability](https://image.slidesharecdn.com/personalauthenticationusing3-dfingergeometrysynopsis-131016121932-phpapp02/85/Personal-authentication-using-3-d-finger-geometry-synopsis-10-320.jpg)
Personal authentication using 3 d finger geometry (synopsis)
- 1. Personal Authentication Using 3-D Finger Geometry (Synopsis)
- 2. INTRODUCTION A problem of personal verification and identification is an actively growing area of research. In our global information society, there is an ever-growing need to authenticate individuals. Biometrics-based authentication is emerging as a reliable method that can overcome some of the identification limitations technologies. of the traditional Automated automatic biometrics personal deal with physiological and/or behavioral characteristics, such as a fingerprint, signature, palmprint, iris, hand, voice or face, which can be used to authenticate a person's claim to a certain identity or establish a person's identity from a large database. With the rapid progress made in electronics and Internet commerce and with the increased emphasis on security, there will be a growing need for secure transaction processing using biometrics technology. The methods are numerous, and are based on different personal characteristics. Voice , lip movements , hand geometry , face , odor ,fingerprint are the most commonly used authentication methods. All of these psychological and behavioral characteristics are called biometrics. The biometrics is most commonly defined as measurable psychological or behavioral characteristic of the individual that can be
- 3. used in personal identification and verification . The driving force of the progress in this field is, above all, the growing role of the Internet and electronic transfers in modern society. Therefore, considerable number of applications is concentrated in the area of electronic commerce and electronic banking systems. Biometrics is expected to be incorporated in solutions to provide for Homeland Security including applications for improving airport security, strengthening our national borders, in travel documents, visas and in preventing ID theft. Now, more than ever, there is a wide range of interest in biometrics across federal, state, and local governments. Congressional offices and a large number of organizations involved in many markets are addressing the important role that biometrics will play in identifying and verifying the identity of individuals and protecting national assets. Biometrics are automated methods of recognizing a person based on a physiological or behavioral characteristic. Among the features measured are; face, fingerprints, hand geometry, handwriting, iris, retinal, vein, and voice. Biometric technologies are becoming the foundation of an extensive array of highly secure identification and personal verification solutions. Biometric-based solutions are able to provide for confidential financial transactions and personal data privacy. The need for biometrics can be
- 4. found in federal, state and local governments, in the military, and in commercial applications. Enterprise-wide network security infrastructures, government IDs, secure electronic banking, investing and other financial transactions, retail sales, law enforcement, and health and social services are already benefiting from these technologies. With an increasing emphasis on security, automated personal identification based on biometrics has been receiving extensive attention over the past decade. Biometrics aims to accurately identify each individual using various physiological or behavioral characteristics, such as fingerprints, face, iris, retina, gait, palm-prints and hand geometry etc.
- 5. Overview of the System The physiological biometrics are based on measurements and data derived from direct measurement of a part of the human body. Fingerprint, recognition iris-scan, are retina-scan, leading hand geometry, physiological and facial biometrics. Behavioral characteristics are based on an action taken by a person. Behavioral biometrics, in turn, are based on measurements and data derived from an action, and indirectly measure characteristics of the human body. Voice recognition, keystroke-scan, and signature-scan are leading behavioral biometric technologies. One of the defining characteristics of a behavioral biometric is the incorporation of time as a metric – the measured behavior has a beginning, middle and end. A biometric system is essentially a pattern recognition system which makes a personal identification by determining the authenticity of a specific physiological or behavioral characteristic possessed by the user. An important issue in designing a practical system is to determine how an individual is identified. Depending on the context, a biometric system can be either a verification (authentication) system or an identification system. BIOMETRIC authentication, once used for granting access to high security infrastructures, is gradually finding place in a wider range of
- 6. applications. However, until today the requirement for highly reliable authentication has led to compromises with respect to user acceptance. It is clear that reliability and user convenience should coexist in order to achieve a widespread acceptance of biometrics. The work in this paper is partly motivated by applications where the convenience of the user is the first priority. These applications include personalization of services (home, office, car) and attendance tracking in working environments. A user authentication system based on measurements of three-dimensional (3-D) hand geometry is proposed. Unlike other hand geometry verification techniques the proposed system is less obtrusive. The user is not obliged to place his/her hand on a surface and generally there are less constraints regarding the placement of the hand (e.g., using pegs) or the environment (e.g., uniform background). To achieve this, a low-cost 3-D sensor is used that captures both an image of the hand as well as its 3-D structure, and novel algorithms for robust estimation of 3-D geometric hand features are proposed. Experimental results demonstrate that the accuracy of the system is comparable with state-of-the-art hand geometry recognition systems.
- 7. Abstract A biometric authentication system based on measurements of the user’s three-dimensional (3-D) hand geometry is proposed. The system relies on a novel real-time and low-cost 3-D sensor that generates a dense range image of the scene. By exploiting 3-D information we are able to limit the constraints usually posed on the environment and the placement of the hand, and this greatly contributes to the unobtrusiveness of the system. Efficient, close to real-time algorithms for hand segmentation, localization and 3-D feature measurement are described and tested on an image database simulating a variety of working conditions. The performance of the system is shown to be similar to state-of-the-art hand geometry authentication techniques but without sacrificing the convenience of the user.
- 8. Description of Problem A problem of personal verification and identification is an actively growing area of research. In our global information society, there is an ever-growing need to authenticate individuals. Biometrics-based authentication is emerging as a reliable method that can overcome some of the limitations of the traditional automatic personal identification technologies. With the rapid progress made in electronics and Internet commerce and with the increased emphasis on security, there will be a growing need for secure transaction processing using biometrics technology. The methods are numerous, and are based on different personal characteristics. Voice , lip movements , hand geometry , face , odor ,fingerprint are the most commonly used authentication methods. All of these psychological and behavioral characteristics are called biometrics. The biometrics is most commonly defined as measurable psychological or behavioral characteristic of the individual that can be used in personal identification and verification. The driving force of the progress in this field is, above all, the growing role of the Internet and electronic transfers in modern society. Therefore, considerable number
- 9. of applications is concentrated in the area of electronic commerce and electronic banking systems. Existing Method Hand geometry recognition is one of the most popular biometrics used today for user verification. It works by comparing the 3-D geometry of the hand with a previously enrolled sample. A simple two-dimensional (2-D) camera sensor is commonly used to capture an image of the user’s palm, while a lateral view of the hand is captured on the same CCD thanks to a mirror. The user has to put his/her hand on a special platter with knobs or pegs that constrain the placing of the hand on the platter. This greatly simplifies the process of feature extraction performed by analyzing the image contours of the hand views. Various features such as width of the fingers, length of the fingers and width of the palm have been proposed. Satisfactory recognition results are obtained (96% for recognition and less than 5% EER 1 for authentication). Instead of using measurements of the hand for verification, uses pointsonahandsilhouette contour as features, while matching is based on the mean alignment error between two sets
- 10. of silhouette points. The authentication accuracy of the system for a database of 53 person was about 2% FAR and 1.5% FRR. The major limitation of the above approaches is their obtrusiveness imposed by the use of pegs, which constrain the positioning and posture of the hand. Moreover, correct placement of the hand requires some training, and presents difficulties for specific user groups such as young children and elderly. Therefore, several researchers have proposed to remove the requirement for pegs, and use a document scanner or back-lit display for acquisition of hand images. In a feature-based approach is used and an FRR close to 3% was achieved for an FAR of 1% on a database of 70 people. Also extracts hand features from hand silhouettes and employees a hierarchical authentication scheme. For a database of 22 people FRR at 12% for FAR at 2.22% is reported. Finally in [6], implicit polynomials are fitted on hand contours and geometric invariants are subsequently computed from these polynomials. The invariants are then combined with geometric hand features to perform matching and an FRR of 1% for an FAR of 1% on a small database (45 images) is reported. The problems are: o Easily traceable by intruders o Low reliability
- 11. o No unique identification In these methods entire image is used for feature extraction. Proposed System The biometrics have a significant advantage over traditional authentication techniques (namely passwords, PIN numbers, smartcards etc.) due to the fact that biometric characteristics of the individual are not easily transferable, are unique of every person, and cannot be lost, stolen or broken. The choice of one of the biometric solutions depends on several factors : User acceptance Level of security required Accuracy Cost and implementation time In previous methods, entire image is used for feature extraction. But here in this proposed algorithm 3d geometry points of the segmented finger are extracted and feature points are extracted from
- 12. these points. In the proposed method the images are captured and kept in the data folder in my application. The proposed algorithm is invariant of the camera calibration. The image is passed through four stages before extracting feature points. In the first stage, the input image is threshold in order to segment the finger from the background. Then this image is passed to second stage, where finger boundary points are extracted by linear edge detection. Then this image is passed to third stage, which is simple enlargement. That is, the finger boundary image is placed inside a large image in this stage. This is done in order to find/select the geometry points from the boundary points of the finger. In other words the image is enlarged so that the entire edge-image is fit in the center and geometry-lines can be projected from outer. Using this enlarged image as input, the geometry points of the finger are found. for this, a large circle is drawn around the finger in the enlarged image and from each
- 13. circle point (360 degree) one line is drawn towards the center and the point (x,y) in that line where first edge pixel of the finger is found is stored. During recognition, feature vector for test-image is found and compared with all feature vectors of training images. The euclidean-distance between test vector and training vectors are found and the matched image is the image with smallest distance. accuracy is 100-r where r is the ratio between smallest and maximum distance. The main difference of our approach in comparison with the above techniques is that less constraints are posed on the placement of the hand and the on environment. Working on a combination of color and 3-D information, we present robust algorithms which are capable of withstanding in some degree, cluttered background, illumination variations, hand pose, finger bending and appearance of rings. There are certainly limitations on the working conditions under which the system may operate reliably, e.g., working outdoors or under large pose and finger bending conditions may be problematic. However, these constraints are far less than those imposed by existing systems.
- 14. Module Design The entire project is categorized into four modules as follows: • Image Files Processing The finger print images are first trained to the system. First training is successfully completed then only system takes the test process. Unsupervised learning - this is learning from observation and discovery. The data mining system is supplied with objects but no classes are defined so it has to observe the examples and recognize patterns (i.e. class description) by itself. This system results in a set of class descriptions, one for each class discovered in the environment. Again this is similar to cluster analysis as in statistics. • Image Enhancement Segmentation: taking only the image of finger print portion excluding eyelids and eyelashes. The normalized finger print image has low contrast and may have nonuniform brightness caused by the position of light sources. All these may affect the subsequent processing in feature extraction and matching. In order to obtain a more well-distributed texture image, we first approximate intensity variations across the whole image. The mean of each 16 * 16 small block constitutes a coarse estimate of the background illumination.
- 15. This estimate is further expanded to the same size as the normalized image by bicubic interpolation. • Finger print Feature Extraction in this proposed algorithm 3d geometry points of the segmented finger are extracted and feature points are extracted from these points. In the proposed method the images are captured and kept in the data folder in my application. The proposed algorithm is invariant of the camera calibration. The image is passed through four stages before extracting feature points. In the first stage, the input image is threshold in order to segment the finger from the background. Then this image is passed to second stage, where finger boundary points are extracted by linear edge detection. Then this image is passed to third stage, which is simple enlargement. That is, the finger boundary image is placed inside a large image in this stage. This is done in order to find/select the geometry points from the boundary points of the finger. In other words the image is enlarged so that the entire edge-image is fit in the center and geometry-lines can be projected from outer.
- 16. Using this enlarged image as input, the geometry points of the finger are found. for this, a large circle is drawn around the finger in the enlarged image and from each circle point (360 degree) one line is drawn towards the center and the point (x,y) in that line where first edge pixel of the finger is found is stored. During recognition, feature vector for test-image is found and compared with all feature vectors of training images. The euclidean-distance between test vector and training vectors are found and the matched image is the image with smallest distance. accuracy is 100-r where r is the ratio between smallest and maximum distance.
- 17. Hardware specifications: Processor RAM : : Intel Processor IV 128 MB Hard disk : 20 GB CD drive : 40 x Samsung Floppy drive : 1.44 MB Monitor : 15’ Samtron color Keyboard Mouse : : 108 mercury keyboard Logitech mouse Software Specification Operating System – Windows XP/2000 Language used – J2sdk1.4.0