(IJCSIS) International Journal of Computer Science and Information Security,Vol. 9, No. 7, July 2011
Experimental results of this work show that the system isvalid for user authentication purpose even in high securityenvironments, as it was the initial intention given the nature of human finger vein.II.
SYSTEMThe steps of finger vein authentication system are explained inthe following.
The first step in finger vein authentication system iscapturing the image of finger veins. The quality of capturedimage helps to identify the veins of fingers as well. ImageAcquisition can be done in two ways; i) using infrared-sensitive digital camera with wavelength between 700nm to1000nm and banks of LEDs ; ii) using digital camera withCCD sensor and IR filter which is located on the camera withwavelength 700nm to 1000nm and banks of LEDs .Therefore, as shown in figure 2, the Near-infrared raysgenerated from a bank of LEDs (light emitting diodes)penetrate the finger and are absorbed by the hemoglobin in theblood. The areas in which the rays are absorbed (veins) thusappear as dark areas in an image taken by a CCD camera(charge-coupled device) located on the opposite side of thefinger. The CCD camera image will be transferred to PC fornext step of authentication .
Figure 2. Image Acquisition system
As stated above, the better quality can make recognitionsystem more accurate. For this purpose, the noise is reduced onnext step.
As the image has been taken by camera has redundant partswhich needs to be cropped. Therefore, only the central part of finger vein image can be taken in Matlab by a simple line;(1)I2= imcrop (I, rect);
Where „I‟ is an image and „rect‟ is the position for
cropping.The next step in this section is reducing the noise of fingervein image to improve segmentation. Since the captured imagehas much noise, therefore it needs to be improved for gettingbetter quality. For this purpose, the enhancement Functions
such as ‟medfilt2‟, „medfilt2‟ can be employed. As the final
step for image pre-processing, the image contrast can be
increased using commands in Matlab such as „histeq‟.
Figure 3shows the total process for enhancing the image.
Reducing noiseIncreasing contrast
Figure 3. Image enhancement process
Segmentation and Feauture extractions
In this stage, the enhanced finger vein image is segmentedand the features are extracted. Since there are different methodsfor segmentation, this paper propose the combination of twosegmentation methods as
Gradient-based thresholding usingmorphological operation
Maximum Curvature Points inImage Profiles
to segment and extract the features. Thefeatures of first segmentation method are merged with featuresof second segmentation method to obtaine an accurate recordfor each finger vein images.1)
Gradient-based thresholding using morphologicaloperation:
In this segmentation method, the gradient of image by alpha filter is created. Then, thresholding isperformed on gradient of image. The high gradient valueswhich are more than threshold value in the image fall asedge (vein). After the vein determination in an image, themorphological operations are employed to make an imagesmoother. The proposed morphological operations are
„majority‟ to remove extra pixels, „openning‟ to smoothsthe contour of image and breaks narrow passages, „bridge‟
to connects the neighbor pixels which are disconnected.The original and obtained image after first segmentationmethod (includes performing gradient, thresholding,morphological operation) are shown in figure 4.
a bFigure 4. a) Original image b) Obtained image after firstsegmentation
The total process for the
Gradient-based thresholdingusing morphological operation
method is shown as figure 5.