Contact Vs Contact-less Fingerprint Biometric Systems 1
Vineet Srivastava Abhay Chaturvedi Department of Computer Science & Engineering Dehradun Institute of Technology, Dehradun (Uttarakhand) 1
[email protected] 2
[email protected] 2
Abstract— The term Biometric comes from the Greek words bios (life) and metron (measurement) therefore in biometric systems the physiological data of human being extracted under a featured set for measurement and analysis to compare against a template set in the database. The major categories of biometric recognition systems works on fingerprint, face, iris, hand geometry, gait, ear, palmprint etc. In this paper a survey of fingerprint biometric systems are discussed for the pattern acquisition under contact and contact-less methods. In traditional system a fingerprint image captured by a contact-based sensor but in contact-less approach fingerprints images are captured without any user contact with sensor. Contact-less approach overcomes different types of problems like redundancy due to noise, low or high pressure during fingerprint impression for the same user. Keywords—Biometric, Fingerprints, Pre-processing
Contact-based,
Contact-less,
I. INTRODUCTION A biometric system is essentially a pattern recognition system in which any human physiological or behavioral trait serves a biometric characteristic as long as it satisfies universality, distinctiveness, permanence and collectability. Three more factors should be considered in real life applications such as performance, acceptability and circumvention i.e. it should be robust enough to various fraudulent methods. A simple biometric system consists of four basic components: 1) Sensor module which acquires the biometric data; 2) Feature extraction module where the acquired data is processed to extract feature vectors; 3) Matching module where feature vectors are compared against those in the template; 4) Decision-making module in which the user's identity is established or a claimed identity is accepted or rejected. Biometric system can operate in two modes: Identification: An individual is recognized by comparing with an entire database of templates to find a match. The
system conducts one-to-many comparisons to establish the identity of the individual. The individual to be identified does not have to claim an identity Verification (authentication): An individual to be identified has to claim his/her identity and this template is then compared to the individual's biometric characteristics. The system conducts one-to-one comparisons to establish the identity of the individual. Before a system is able to verify/identify the specific biometrics of a person, the system requires something to compare it with. Therefore, a profile or template containing the biometric properties is stored in the system. Recording the characteristics of a person is called enrollment. Fingerprint recognition is the technology that satisfies the identity of a person based on the fact that everyone has unique fingerprints. It is one of the most heavily used and actively studied biometric technologies. A. Why Fingerprints? The cost of a fingerprint based biometric system is quite low in comparison to others like iris and face readers. Fingerprint based systems are quite strong and can be deployed across any kind of environment. This system is less intrusive than iris or retina scans. Finger based systems are more user friendly.
Fig. 1: Fingerprint Image B. Principles of fingerprint biometrics A fingerprint is made of a number of ridges and valleys on the surface of the finger. Ridges are the upper skin layer segments of the finger and valleys are the lower segments. The uniqueness of a fingerprint can be determined by the pattern of ridges and furrows as well as the minutiae points.
A. Issues with contact- based fingerprint biometric systems
Whorl
Tented Arch
Loop
Arch
Fig. 2: Types of Fingerprint Images
When a finger is very dry, it does not make uniform and consistent contact with the FTIR imaging surface. The tip of the finger is a small area from which to take measurements, and ridge patterns can be affected by cuts, dirt etc. Acquiring high-quality images of distinctive fingerprint ridges and minutiae is complicated task. People with no or few minutia points cannot enroll or use the system. The number of minutia points can be a limiting factor for security of the pattern recognition algorithm. Results can also be confused by false minutia points i.e. areas of obfuscation that appear due to lowquality enrollment, imaging, or fingerprint ridge detail. These conventional fingerprint systems are simple but they suffer from various problems such as hygienic, maintenance and latent fingerprints. Contamination problem occurs because of placing the fingertip over the same interface which is already used by others. This produces a low quality fingerprint image. Another problem is due to contact pressure which creates physical distortions which are usually non-linear in arbitrary direction and strength.
There are some basic fingerprint patterns: arch, tented arch, loop and whorl. Loops make up 60% of all fingerprints, whorls account for 30%, and arches for 10%. Fingerprints are usually considered to be unique, with no two fingers having the exact same dermal ridge characteristics.
Fig. 3: Ridges on a finger
II. CONTACT-BASED FINGERPRINT BIOMETRIC SYSTEM Frustrated Total Internal Reflection (FTIR) is the oldest and most commonly used live-scan acquisition technique today. As the finger touches the top side of a glass/plastic prism, the ridges are in optical contact with the prism surface, but the valleys remain at a certain distance as can see in Fig. 4. The left side of the prism is typically illuminated through a diffused light (a bank of light-emitting diodes [LEDs] or a film of planar light). The light entering the prism is reflected at the valleys, and randomly scattered (absorbed) at the ridges. The lack of reflection allows the ridges (which appear dark in the image) to be discriminated from the valleys (appearing bright). The light rays exit from the right side of the prism and are focused through a lens onto a CCD or CMOS image sensor. Because FTIR devices sense a three-dimensional finger surface, they cannot be easily deceived by presentation of a photograph or printed image of a fingerprint.
Fig. 4: FTIR-based fingerprint sensor operation B. Possible solution to overcome contact-based issues A Contact-less or Touch-less based fingerprint recognition system could be a reliable alternative to conventional contactbased fingerprint recognition system. Contact-less system is different from conventional system in the sense that they make use of digital camera to acquire the fingerprint image whereas conventional system uses live-acquisition techniques. Contactless fingerprint sensor provides deformation free, highquality fingerprint image. Contact-less fingerprint sensor offers to users a cleaner and more comfortable measurement environment because cleaning and sanitation of sensor not necessary due to lack of physical contact. Therefore, no latent fingerprints and no deformation of fingerprint patterns without any physical pressure of finger to the optical sensor based biometric systems.
III. CONTACT-LESS FINGERPRINT BIOMETRIC SYSTEM A contact-less fingerprint recognition system is a technology which allows us to take fingerprint images without any physical contact of sensing surface. The contact-less system makes use of contact-less fingerprint acquisition to capture the ridge-valley pattern. Contact-less fingerprint recognition systems uses digital camera to acquire the fingerprint image. There is an advantage of using digital camera i.e. the fingerprint images captured with contact-less device are distortion free and present no deformation because these images are free from the pressure of contact. The contact-less fingerprint recognition system can be divided into three main modules: preprocessing, feature extraction and matching. Preprocessing is an important step prior to fingerprint feature extraction and matching. Further preprocessing is divided into four parts: first is normalization, second is fingerprint Segmentation, third is fingerprint enhancement and last is the core point detection. Feature extraction can be done by Gabor filter or by minutia extraction and the matching can be done by Support Vector Machine or Principal Component Analysis and three distance method. The block diagram of a contact-less fingerprint recognition system is shown in following Fig. 5.
which are sufficient for recognition of most natural objects. Grayscale conversion can be performed by following function:
where,
y= f(x) x: original input data y: converted output data
B. Normalization The fingerprint images captured by digital camera are in RGB format so RGB to grayscale conversion is done before normalization. We use fingerprint image normalization to remove the non-uniform lighting problems by changing the dynamic range of pixel intensity values. For this we first calculate the mean and variance i.e. standard deviation to reduce the differences of illumination and perform normalization by the following formula: g(x,y) = {f(x,y) – mf(x,y)}/σf(x,y) where, f(x,y) : the original image mf(x,y) : estimation of mean f(x,y) σf(x,y) : estimation of the standard deviation C. Skin Color Detection Skin color detection is a decision rule which discriminate between skin and non-skin pixels. This is usually accomplished by introducing a metric which measures the distance of the pixel color to skin tone. D. Adaptive Thresholding The fingerprint images possess ridge flow patterns with slowly changes in directions. They may have various gray-level values due to non-uniformity of illumination and contrast during image acquisition process. Therefore adaptive Thresholding technique is used to binarize fingerprint images, binarization depends on the comparison result of gray-level value of each pixel with local mean for further feature extraction.
Fig. 5: Block diagram of the Contact-less Fingerprint Recognition System IV. PRE-PROCESSING Preprocessing is an important step prior to fingerprint feature extraction and matching in contact-less biometric systems. Since the fingerprint images are captured using digital camera therefore problems like motion, contrast and alignments could occur. Generally preprocessing is analyzed under normalization, segmentation, enhancement and core point detection of a fingerprint image. A. Grayscale Conversion Grayscale conversion is a simple image enhancement technique because a grayscale has 256 different gray levels
E. Morphological Processing In morphological image processing techniques we extract image components that are useful in representing and describing region shapes. The filters can be described using set theoretic notation and implemented using simple computer algorithms based on these. F. Image Enhancement Image enhancement is the conversion of the image quality to a better and more understandable level for feature extraction. G. Core Point Detection A point of maximum curvature in a fingerprint image is known as core point. A fingerprint can have two structures, the global and the local structure. In the global structure the overall pattern of the ridges and valleys are considered where as in local structure the detailed pattern around a minutiae point is considered. The global structure is used because it is more stable even when the fingerprint is of poor quality. Core points
have special symmetry properties which make them easy to identify. Core point detection is done by using different complex filtering algorithms through modeling. H. Image Cropping In fingerprint image cropping, the region of interest (ROI) based on reference point is determined and tessellate the region of interest into the number of square cells. Fingerprint images could be cropped generally on the basis of pixel dimensions. I. Feature Extraction It is an operation to quantify the image quality through various parameters and functions which are applied to the original image. Features involved in an image are classified as follows: (1) Special features like color, gradient, spectral parameter etc. (2) Geometric features like edge, shape, size etc. (3) Textural features like pattern, spatial frequency, homogeneity etc. J. Fingerprint Verification At the verification stage, the template from the claimant fingerprint is compared against that of the enrollee fingerprint. This is done usually by comparing neighborhoods of nearby minutiae for similarity.
V. APPLICATIONS OF CONTACT-LESS FINGERPRINT TECHNOLOGY
Increased accuracy of contact-less fingerprinting facilitates its new applications in both the private and public sectors. . A. Law Enforcement Agencies Every organization has unique requirements for stored fingerprints depending on how these prints are utilized. The specific need of individual organizations has resulted in different agencies having their own unique and often incompatible databases. Recently, creation of a unified and accurate database across all agencies has been recognized as a necessary step in the evolution of law enforcement’s capabilities. B. Access Control Access control can also benefit from such devices. Current fingerprint based access control devices have a certain disadvantage in usability. Often a user may need to repeatedly scan their finger before they are granted access. The need to use a finger few times is caused by inconsistencies between the fingerprints data recorded by the capture device and the data stored within the system’s database. This inconsistency increases the systems margin of error, translates to increased false rejections and a lower degree of confidence with every match. In high security access control, an additional measure can be taken to further increase the degree of confidence with every match. Spoof detection is a technique that focuses on
determining whether a finger is currently alive and attached to the body and is in fact the person’s real finger. C. Financial Transaction In the commercial sector, accurate biometric based authentication can be implemented in electronic commerce and confidential email exchange. Methods of authentication such as tokens, cards, badges, passwords and pins are widely being used today. These methods can be supplemented by accurate fingerprint based authentication to obtain a higher degree of user confidence and decrease the presence of fraud in online transactions. At places of financial transactions, Automatic Teller Machines and E-commerce are all areas that can potentially find solutions to long-standing security related problems through the use of commercialized contact-less fingerprinting devices. VI. CONCLUSION In this study of Contact Vs Contact-less fingerprint biometric systems we discusses many demerits of our traditional fingerprint recognition systems and as a solution to overcome those deficiencies a new approach of contact-less fingerprint biometric system studied. As there are strong advantages of using digital camera in contact-less system but there appears contrast problems between ridges and valleys in fingerprint images obtained. Because the depth of the field of the camera is small thus some part of the fingerprint regions are in focus and some parts are out of focus. Another problem of motion blurriness in the acquired images due to not fixed sensor surface. Thus in the future, improvement in these areas could be possible by putting main concern on the fingerprint image preprocessing techniques. REFERENCES [1] [2]
http://en.wikipedia.org/wiki/Fingerprint.
Davide Maltoni, Dario Maio,Anil K. Jain, Salil Prabhakar “Handbook of Fingerprint Recognition”: Second Edition, Springer. [3] Prabhjot Kaur, Ankit Jain, Sonia Mittal “Touch-less Fingerprint AnalysisA Review and Comparison”, I.J. Intelligent Systems and Applications, 2012, 6, 46-52 Published Online June 2012 in MECS (http://www.mecspress.org/) DOI:10.5815/ijisa.2012.06.06 [4] S. Mil’shtein*, V. Oliyil Kunnil, C. McPherson , A. Pillai “Handheld Imaging System for Contactless Tri-Modal Biometric Identification” American Journal of Biomedical Engineering: 2011; 1(2): 68-71 DOI: 10.5923/j.ajbe.20110102.12. [5] Anil K. Jain, Patrick Flynn Arun A. Ross, “Handbook of Biometrics”, Springer. [6] H B Kekre, V A Bharadi, “Fingerprit Core Point Detection Algorithm Using Orientation Field Based Multiple Features”, International Journal of Computer Applications (0975 - 8887) Volume 1 – No. 15
