Read without ads and support Scribd by becoming a Scribd Premium Reader.
See Premium Plans
 
 COLLEGE SCIENCE IN INDIA
Pay Attention, Gain Understanding
Vol. 1 : 3 December 2007
 
Board of Editors
S. Andrews, M.Sc., M.Phil., Editor-in-Chief S. Lalitha, Ph.D.Poornavalli Mathiaparnam, M.A., M.Phil.M. S. Thirumalai, Ph.D., Managing Editor

Webcam Based FingerprintAuthentication for Personal IdentificationSystem
Md. Rajibul Islam, Md. Shohel Sayeed, and Andrews Samraj
College Science in India 1 : 3 December 2007Webcam Fingerprint Personal IdentificationIslam, Sayeed & Samraj 1
 
Webcam Based Fingerprint Authentication forPersonal Identification System
Md. Rajibul Islam, Md. Shohel Sayeed, Andrews Samraj
 Abstract
: In the networked world there are a hugenumber of systems that need biometric recognition, so atpresent it has become an important issue. For the personalidentification various kinds of vision-based techniques havebeen proposed earlier. We present a novel one based onvisual capturing of fingerprints using a webcam.Fingerprint image quality influences deeply theperformance of fingerprint identification systems. Thispaper presents an improved authentication system using alow priced webcam as well as a preprocessing approachusing gamma manipulation and gamma correctiontechnique to adjust lightness and intensities of thefingerprint image due to enhance fingerprint image quality.We also implement and test our proposed approach usingthe FVC2004 database including the webcam database of 1200 fingerprint images which is obtained by proposedapproach and compare the EER (Equal Error Rate), FRR(False Rejection Rate) and FAR (False Acceptance Rate) of each database. Experiment- al results show that ourapproach performs significantly improved andcomparatively EER, FRR, FAR of the webcam databaseare very similar to the FVC2004 database.
 Index Terms
- fingerprint authentication, web- cam,fingerprint, fingerprint sensor, gamma manipulation,gamma correction.I. I
NTRODUCTION AND
M
OTIVATION
 
Biometrics proposes an effectual approach to identify subjectsbecause it is concerned with the unique, reliable and stablepersonal physiological features. These features can be: iris [8],[9], fingerprints [6], [7], palmprints [10], [11], hand geometry[12], [13], faces [14], [15], voice [16], [17], etc. Most of themare used for Vision based identification. Voice recognition orsignature verification are the most widely known among thenon-vision based ones. Among these, fingerprint identificationhas been the most widely browbeaten because of stability,usability, and low cost. A fingerprint sensor is necessary forthe commercial fingerprint identification system. Unfortunatelyalmost all the modern sensor products are not so cheap andavailable in the market. Therefore we’ve used a low pricedwebcam to fabricate our authentication system. But there arechallenging problems when developing fingerprintidentification system using a webcam. First, the contrastbetween the ridges and the valleys in images obtained with awebcam is low. Second, because of the finger is not flat andthe image captured by webcam is low resolution image, someparts of the fingerprint regions are clear but some parts areblurred, even it is impossible to extract ridges and valleys.Third, the lightness of captured fingerprint image is so brightand blur. The overall fingerprint identification system using awebcam is composed of preprocessing using gammamanipulation and gamma correction, image enhancement,feature extraction, and matching algorithm. Fig. 3 shows theblock diagram of the overall system.This paper presents an overview of the whole interface and anovel approach to capture fingerprint images using webcamand preprocessing these images in order to improve theenhancement and extraction system. We have divided thispaper in the following way: In the next part of this section,briefly presents an overview of some fingerprint scanner. Insection 2, we describe about the webcam dataset, datacollection, overview of the whole system, our contributionespecially gamma manipulation and gamma correctiontechnique of the preprocessing stage before imageenhancement and feature extraction in our authenticationsystem. After that, in section 3, we describe the experiments,discussions using the data obtained from the proposedapproach and the data from FVC2004 and a comparative resultalso presented. Possible future work perspectives is describedin section 4 and by the end of this paper, we presentconclusion.
 A. Overview of some Fingerprint Sensors
We may not realize it, but the ridges in our fingertips haveevolved over the years to allow us to grasp and grip objectswith our hands. The ridges and valleys of skin are formedbased on genetic and environmental factors, thus, fingerprintsare said to be unique from individual to individual. Evenidentical twins do not share the same fingerprints.A fingerprint sensor is an electronic device used to capture adigital image of the fingerprint pattern. The captured image iscalled a live scan. This live scan is digitally processed to createa biometric template (a collection of extracted features) whichis stored and used for matching. Following are the overview of some of the more commonly used fingerprint sensortechnologies [18].There are two basic methods for scanning fingerprints: Opticalscanning and capacitance scanning. Besides Ultrasonic sensorsalso have been used to scan fingerprint.
College Science in India 1 : 3 December 2007Webcam Fingerprint Personal IdentificationIslam, Sayeed & Samraj 2
 
Optical
Optical fingerprint imaging involves capturing a digital imageof the print using visible light. This type of sensor is, inessence, a specialized digital camera. The top layer of thesensor, where the finger is placed, is known as the touchsurface. Besides this layer is a light-emitting phosphor layerwhich illuminates the surface of the finger. The light reflectedfrom the finger passes through the phosphor layer to an arrayof solid state pixels (a charge coupled device) which captures avisual image of the fingerprint. A scratched or dirty touchsurface can cause a bad image of the fingerprint. Adisadvantage of this type of sensor is the fact that the imagingcapabilities are affected by the quality of skin on the finger.For instance, a dirty or marked finger is difficult to imageproperly. Also, it is possible for an individual to erode the outerlayer of skin on the fingertips to the point where the fingerprintis no longer visible. It can also be easily fooled by an image of a fingerprint if not coupled with a "live finger" detector.However, unlike capacitive sensors, this sensor technology isnot susceptible to electrostatic discharge damage.
Capacitance
Like optical scanners, capacitive fingerprint scanners generatean image of the ridges and valleys that make up a fingerprint.But instead of sensing the print using light, the capacitors useelectrical current.Capacitance sensors utilize the principlesassociated with capacitance in order to form fingerprintimages. The two equations used in this type of imaging are:
V QC 
=
………(1)
d  AC 
r o
∈=∈
………..(2)Where
C 
is the capacitance in farads
Q
is the charge in coulombs
V 
is the potential in volts
0
is the permittivity of free space, measured in farad per meter
r 
is the dielectric constant of the insulator used
 A
is the area of each plane electrode, measured in squaremeters
d 
is the separation between the electrodes, measured in meters.In this method of imaging, the sensor array pixels each act asone plate of a parallel-plate capacitor, the dermal layer (whichis electrically conductive) acts as the other plate, and the non-conductive epidermal layer acts as a dielectric.
Passive capacitance
A passive capacitance sensor uses the principle outlined aboveto form an image of the fingerprint patterns on the dermal layerof skin. Each sensor pixel is used to measure the capacitance atthat point of the array. The capacitance varies between theridges and valleys of the fingerprint due to the fact that thevolume between the dermal layer and sensing element invalleys contains an air gap. The dielectric constant of theepidermis and the area of the sensing element are knownvalues. The measured capacitance values are then used todistinguish between fingerprint ridges and valleys.
Active capacitance
Active capacitance sensors use a charging cycle to apply avoltage to the skin before measurement takes place. Theapplication of voltage charges the effective capacitor. Theelectric field between the finger and sensor follows the patternof the ridges in the dermal skin layer. On the discharge cycle,the voltage across the dermal layer and sensing element iscompared against a reference voltage in order to calculate thecapacitance. The distance values are then calculatedmathematically, using the above equations, and used to form animage of the fingerprint. Active capacitance sensors measurethe ridge patterns of the dermal layer like the ultrasonicmethod. Again, this eliminates the need for clean, undamagedepidermal skin and a clean sensing surface.
Ultrasonic
Ultrasonic sensors make use of the principles of medicalultrasonography in order to create visual images of thefingerprint. Unlike optical imaging, ultrasonic sensors use veryhigh frequency sound waves to penetrate the epidermal layer of skin. The sound waves are generated using piezoelectrictransducers and reflected energy is also measured usingpiezoelectric materials. Since the dermal skin layer exhibits thesame characteristic pattern of the fingerprint, the reflectedwave measurements can be used to form an image of thefingerprint. This eliminates the need for clean, undamagedepidermal skin and a clean sensing surface.
Webcam
Webcams typically include a lens, an image sensor, and somesupport electronics [19]. Various lenses are available, the mostcommon being a plastic lens that can be screwed in and out toset the camera's focus. Image sensors can be CMOS or CCD,the former being dominant for low-cost cameras, but CCDcameras do not necessarily outperform CMOS-based camerasin the low cost price range. Consumer webcams usually offer aresolution in the VGA region, at a rate of around 25 frames persecond. The higher resolution of 1.3 Megapixel is alsoavailable in the market.The camera pictured to the right, for example, uses a SonixSN9C101 to transmit its image over USB. Some cameras -such as mobile phone cameras - use a CMOS sensor withsupporting electronics 'on die', i.e. the sensor built on a singlesilicon chip, to save space and manufacturing costs.
College Science in India 1 : 3 December 2007Webcam Fingerprint Personal IdentificationIslam, Sayeed & Samraj 3
Search
Search History:
Searching...
Result 00 of 00
00 results for result for
  • p.
    • Notes
    Load more