Abstract – This paper suggests a new and improved method of authentication technique by the hand vein structure. Such a fast and hygienic biometrics provides highly secured and reliable authentication system by the contactless imaging setup. In this IR camera is used to acquire the image of hand vein. The structure of vein is extracted from the captured IR images and to be evaluated with already stored in database. If the input image matches with the stored one, then only the system will be respond, give access for the person. In this the system performance is improved by the detection of a living person who is authenticating the system. This may avoid the spoofing attack to the system to access the important data. The liveness of a human will be evaluated by the body temperature, oxygen content, speed of blood flow inside the artery vein and relative dielectric constant. This system handles the potential deformations, rotational and translational changes more effectively by encoding the orientation preserving features and utilizing a novel region-based matching scheme.
Keywords: – user authentication, biometrics, hand vein, security system, liveness, vascular biometrics.
Human authentication is one of the most critical and challenging tasks to meet growing demand for security system. A biometric feature provides a highly secured accessing system. Existing methods of using PIN number, password, key, and etc to identify a person is not much reliable and provide a low level security. It provides more reliable feature than the password based authentication system as biometric traits cannot be lost or forgotten, biometric feature are difficult to forge, and require the person to be present for the authentication process. Many biometric such as face, finger print, iris and voice have been developed and utilized. But here verification using hand vein pattern is not developed much more. Biometric authentication is perform in insecure because of information leakage issue, so overcome this the implementation of biometric hand vein authentication Hand vein structure are the vast network of blood vessels inside a person’s skin. The vein structure is unique to everyone and is stable over a long period of time. It is not easy to capture by human eye. Due to the uniqueness, stability, and high resistance to criminal tampering, vein pattern offers a highly secure and reliable traits for biometric authentication system. This paper proposed a method of human authentication. The proposed system of hand vein image is processing of four stages: 1. acquiring the image of hand vein; 2.extracting the vein pattern from captured image; 3. getting the information about the vein structure; 4. the matching the input with the stored database. The main aim is to extract the shape of vein pattern. The Liveness detection is the capability of a biometric system to check whether the biometric sample presented for verification or identification is alive or not. It should also be able to check whether the biometric feature being captured belongs to the authorized person who is present at the time of capture. When a system fails at this point, it is said to be ‘spoofed’ by the imposter. In this system use one proposed hessian based feature extraction method for hand vein pattern.
II. BLOCK DIAGRAM
Fig. 1: Hand Vein Authentication System.
A. Image Acquisition:
The tissue optical window is in the NIR region of light. In this region light can penetrate relatively deep into the skin and illuminate underlying structures. Therefore infrared imaging is important in vascular imaging, and especially for biometric use. The radiation is safe and offers no significant hazard to the skin, unless it is concentrated to such high degree that it causes burning. Infrared radiating light sources are relatively cheap and commercially available. Infrared sensors to obtain images are
Fig: 2 Image acquisition device
also relatively cheap and commercially available in devices such as CCD cameras. They produce infrared images where regions with a higher intensity of emanating NIR light are brighter, whereas low intensity regions are visualized as dark regions. By making use of the reflectance and absorbance properties of issue and blood infrared images captured after illuminating tissue with NIR light will show darker pixels for vascular regions compared to nonvascular regions. This is the basic principle for extracting a vein pattern from an infrared image.
The hand-vein images in contactless imaging present a lot of translational and rotational variations. Therefore, more stringent preprocessing steps are required to extract a stable and aligned Region Of Interest. The preprocessing steps essentially recover a fixed-size ROI from the acquired images which have been normalized to minimize the rotational, translational, and scale changes. This is followed by the nonlinear enhancement so that the vein patterns from ROI images can be observed more clearly.
1. Image Segmentation and Normalization:
The key objective while segmenting the ROI is to automatically normalize the region in such a way that the image variations, caused by the interaction of the user with the imaging device, can be minimized. In order to make the identification process more effective and efficient, it is necessary to construct a coordinate system that is invariant/robust (or nearly) to such variations. It is judicious to associate the coordinate system with the hand itself since we are seeking the invariance corresponding to it. Therefore, two webs are utilized as the reference points/line to build up the coordinate system, i.e., the web between the index finger and middle finger together with the web between the ring finger and little finger. These web points are easily identified in touch-based imaging but should be automatically generated for contactless imaging. However, our method is more computationally efficient since no additional sampling/computations are required. After segmentation, the ROI images are scaled to generate a fixed size region and the whole process is illustrated.
2. Image enhancement:
The captured images generally appear darker with low contrast. Therefore, image enhancement to more clearly illustrate the vein and texture patterns is required. The system estimate the background intensity profiles by dividing the image into slightly overlapping 32×32 blocks and the average gray-level pixels in each block are computed. Finally, histogram equalization is employed to obtain the normalized and enhanced hand-vein image. the enhancement has been quite successful in improving the details and contrast of the ROI images.
C. Feature extraction
The normalized and enhanced hand-vein images depict curved vascular network/patterns, and these vessels can be approximated by small line segments which are rather curved. Therefore, in this paper, we propose to use two new approaches to extract such line-like hand-vein features. In addition, a neighborhood matching scheme that can effectively account for more frequent rotational, translational variations, and also to some image deformations in the acquired image.
1. Neighborhood Matching Radon Transform
The Radon transform is a useful tool in identification areas because it can effectively capture the directional features in the pattern image by projecting the pattern onto different orientation slices. In mathematics, Radon transform is a projection of a 2D function f (x, y) consisting of a set of line integrals in all directions. The Radon transform of a 2D function f (x, y), denoted as R (x), is defined as its line integrals along a line inclined at an angle from the x -axis and at a distance from the origin. The geometry of Radon transform is indicated in the fig.3 below.
Fig. 3 Geometry of Radon Transform
Let f(x, y) be an image, its continuous Radon transform is defined as follows:
Rf (x,y) = ” f(x,y)??(x’-xcos??- ysin??)dxdy
Where x” (- ‘ to ‘) is the distance of a line from the origin and ‘??[0, ‘] is the angle between the distance vector and x -axis, ??(.) is the Dira ?? -function. The x’-?? space will be referred to as the Radon space.
The resulting template size is inversely proportional to the line width, since each of the possible orientations of line segment is just encoded into one code, for a given/certain line width. This procedure is diagrammatically illustrated in Fig. 6 for a line width of two pixels, six orientation, and a lattice size 16×16.
2. Hessian-Phase-Based Feature Extraction
The local hand-vein image characteristics can be observed using Taylor series expansion in the neighborhood of a point. The local characteristic of an image considering its Taylor expansion in the neighborhood of a point is shown as follows:
This equation estimates the structure of the image up to the second order in scale, where J and H denote for the Jacobian and Hessian matrix, respectively.
For an ideal vessel-like structure in a 2-D image the Eigen values should have the form as shown follows:
|??1| ‘ 0
|??2| >> |??1|
Two local characteristics of image can be measured by analyzing the above two equations. First, the norm of the eigen values will be small at the location where no structure information is shown since the contrast difference is low, and it will become larger when the region occupies higher contrast since at least one of the eigen values will be large. Second, the ratio between |??1| and |??2| will be large when the blob-like structure appears in the local area, and will be very close to zero.
III. SPOOF MANAGEMENT
Liveness detection is the capability of a biometric system to check whether the biometric sample presented for verification or identification is live or not. It should also be able to check whether the biometric feature being captured belongs to the authorized person who is present at the time of capture. When a system fails at this point, it is said to be ‘spoofed’ by the perpetrator: he/she can, for example, gain access to a secured system by presenting fake biometric features (fake artifacts) that belong to an authorized person. Or, as in the example, presenting original biometric features that belong to a dead body and are therefore non-acceptable.
Fig 4. Laser Doppler Anemometer
On the same principle as ultrasound flow measurement lays the laser Doppler flowmetry (also known as anemometry or perfusion) technique: the Doppler effect. In this technique the Doppler shift is detected in light waves that are scattered by moving blood cells. vt is the speed of light in tissue, which is the speed of light c (3.00 * 108 m/s). The light source is a monochromatic laser beam, which is split in a probe and reference beam. Then, the shifted and unshifted light is allowed to interfere on the surface of a sensitive photo detector, a beat frequency will be produced, the detectable component of which is equal to the Doppler shift. Typical frequency shifts detected by a laser-Doppler perfusion monitor using a wavelength of 780 nm in the microcirculation range from 0’20 kHz. This makes the laser Doppler flowmetry technique a better performer for low flow velocities. In an infrared (850 nm) laser diode is used and speeds of 67 cm/s are accurately measured. Moreover, no contact is needed between the sensor and the skin. In this way, the vein pattern can also be made visible.
Blood flow velocity:
The Doppler Effect in general is the change in frequency produced by the scattering of waves by a moving object. Using ultrasound waves in human tissue, the Doppler shift ‘f is given by,
Where, f – the frequency of the ultrasound source.
vs – the velocity of the source which causes the Doppler shift (in this case the moving blood cells).
cos?? – is the beam-vessel angle
vt – the speed of sound in tissue.
This paper presents a biometric system that recognizes the shapes of the vein pattern in the back of the human hands captured using an Infrared camera. Preliminary testing results show that all the vein pattern images in the database have been correctly recognized, and it demonstrates the potential usefulness of such a system. Nevertheless, a number of research issues need to be addressed in the future. First of all, the clearness of the vein pattern in the image is affected by a number of factors such as ambient temperature, nearness of the vein to the skin etc. An investigation is needed into the impact of these factors on the quality of the vein pattern image. Secondly, more experiments need to be carried out using a larger image database for a thorough evaluation on the efficacy of hand vein pattern biometrics. Lastly, it is likely that the vein patterns will be used in conjunction with other biometrics in a multimodal system.
 A. K. Jain and J. Feng, ‘Latent palmprint matching,’ IEEE Trans. Pattern Anal. Mach. Intell., vol. 31, no. 6, pp. 1032’1047, Jun. 2009.
 R. Singh, M. Vatsa, H. S. Bhatt, S. Bharadwaj, A. Noore, and S. S.Nooreyezdan, ‘Plastic surgery: A new dimension to face recognition,’ IEEE Trans. Inf. Forensics Security, vol. 5, no. 3, pp. 411’418, Sep.2010.
 T. Matsumoto, H. Matsumoto, K. Yamada, and S. Hoshino, ‘Impact of artificial ‘gummy’ fingers on fingerprint systems,’ Proc. SPIE, pp. 275’289, 2002.
 Xi Li, Xiangbin Liu , Zhicheng Liu ‘A Dorsal Hand Vein Pattern Recognition Algorithm’ 2010 3rd International Congress on Image and Signal Processing (C,ISP2010).
Wang Lingyu and Graham Leedham, ‘Near- and far- infrared imaging for vein pattern biometrics,’ Proc. of the IEEE
International Conference on Video and Signal Based Surveillance (AVSS 06), IEEE Press, Nov 2006, pp. 52, doi:
 Septimiu Crisan, Ioan Gavril Tarnovan, and Titus Eduard Crisan, ‘A low cost vein detection system using near infrared radiation’, IEEE Sensors Applications Symposium, San Diego, pp. 1- 6, February 2007.
 Haifen Chen, Guangming Lu, and Rui Wang, ‘A new palm vein matching method based on ICP algorithm,’ Proc. of 2nd
International Conference on Interaction Science (ICIS 09), ACM Press, Nov. 2009,
 L.Y. Wang, G. Leedham, and D.S.Y. Cho, ‘Minutiae feature analysis for infrared hand vein pattern biometrics’,