Upload
doannga
View
217
Download
3
Embed Size (px)
Citation preview
© 2014, IJARCSSE All Rights Reserved Page | 194
Volume 4, Issue 6, June 2014 ISSN: 2277 128X
International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com
Fingerprinting Enhancement Technology Swati Gupta
* Meenakshi Sharma
CSE & Kurukshetra University CSE & KurukshetraUniversity
India India
Abstract— The main aim of this paper is to enhanced the fingerprint technology. The design will improve scalability,
accessibility and flexibility. This target can be mainly decomposed into image pre-processing, feature extraction and
feature match. My demonstration program is coded by MATLAB. For the program, some optimization at coding level
and algorithm level are proposed to improve the performance of my fingerprint recognition system. For each sub-task,
some classical and up-to-date methods in literatures are analyzed. A pre-processing method consisting of field
orientation, ridge frequency estimation, Gabor filtering, feature extraction and enhancement is performed. The
objective of this project is to present a better and enhanced fingerprint image.
Keywords— Automatic fingerprint identification system (AFIS), American National Standards Institute (ANSI),
Automatic Fingerprint Authentication System (AFAS), Mean Squared Error (MSE), Peak Signal Noise Ratio
(PSNR).
I. INTRODUCTION
The most popular and widely used bio-identification system is fingerprint recognition system because of the fact that
fingerprints of human are unique. Fingerprints of twins are different [3]. Fingerprints have been used for the most widely
used form of biometric identification. The fingerprint of every person is unique and remains unchanged over a lifetime
[1]. Fingerprints are the traces of an impression from the friction ridges and valleys of any part of a human. A fingerprint
can be seen as smoothly varying pattern formed by alternating crest (ridges) and troughs (valleys) on the surface of the
finger as shown in Fig. 1.The ridges are the dark lines and valleys are the light lines in the fingerprint image pattern [3].
A ridge is define as a single curved section, and a valley is the region between two contiguous ridges [1].Fingerprint
detection and analysis has been one of the most common and important forms of crime scene forensic investigation.
Fig 1. Example of a ridge ending and a bifurcation.
Automatic fingerprint identification system (AFIS) is based on the minutiae matching. The (ANSI) American National
Standards Institute has consist of four classes: terminations, bifurcations, trifurcations (or crossover) and undetermined.
The major minutia features of fingerprint ridges are ridge ending, bifurcation, and short ridge (or dot). The ridge ending
is the point at which a ridge terminates. Short ridges (or dots) are ridges which are significantly shorter than the average
ridge length on the fingerprint.
The finger print acquisition can be classified into two major techniques (i) Automatic Fingerprint Recognition with the
help of online sensors or other devices. And another technique is on latent prints which are obtained by various medias
such as ink, powder, paper etc, mostly they are by crime sections [4].
Fig 2: Automatic Finger Recognition System [4].
Gupta et al., International Journal of Advanced Research in Computer Science and Software Engineering 4(6),
June - 2014, pp. 194-200
© 2014, IJARCSSE All Rights Reserved Page | 195
The fingerprint recognition problem can be classified into two sub-domains: (i) fingerprint verification (ii) fingerprint
identification. Fingerprinting verification is used to verify the identity of one person and either accepts or rejects the
user’s identity by matching against an existing fingerprint database. The user provides his fingerprint together with his
identity information like his ID number [4].
The fingerprint verification system retrieves the fingerprint template according to the ID number and matches the
template with the real-time acquired fingerprint from the user. Usually it is based on the design principle of AFAS
(Automatic Fingerprint Authentication System). To design a minutia extractor, a three-stage process is used by
researcher’s i.e preprocessing, minutia extraction and post processing stage [Figure 3].
Fig 3: Automatic Fingerprint Recognition System Extractor [4].
Fingerprinting images are of perfect quality. It may be degraded and corrupted with elements of noise due to many
factors such as scars and moist areas. This degradation can result in a significant number of minutiae being created and
genuine minutiae being ignored and to recover original finger print from noises called pre-processing. Finger printing
enhancement method is used to improve the quality of the image by increasing brightness, contrast, sharpness etc.
II. METHODOLOGY
Fig 4: Steps in Image Enhancement.
A. HISTOGRAM EQUALIZATION
First step of the fingerprinting image enhancement technique is histogram equalization is applied to enhance the
image’s contrast by transforming the intensity values of the image (the values in the colour map of an indexed
image).
Gupta et al., International Journal of Advanced Research in Computer Science and Software Engineering 4(6),
June - 2014, pp. 194-200
© 2014, IJARCSSE All Rights Reserved Page | 196
B. SEGMENTATION
This step is done to separate the actual fingerprint area from the image background. The image is divided into many
blocks and the standard deviation is calculated from the local neighbourhood. A threshold is set to exclude the
background from the fingerprint area [7].
C. RIDGE ORIENTATION ESTIMATION
This step is done to estimate the orientation of the image. The process is carried out by placing an image window at a
point in the raw image. The window is rotated in 16 equally spaced directions and the projections are calculated
along the y direction. The projection with maximum variance is fixed as the orientation of the pixel. This is
continuously done to obtain the values for all the pixels [7].
D. RIDGE FREQUENCY ESTIMATION
Ridge frequency estimation is used for the finger print image by dividing it into blocks of 8 x 8 pixels..An oriented
window (oriented in the direction orthogonal to the local ridge orientation) is used to approximate this sinusoid. The
inverse of the average distance between the numbers of peaks encountered is the local frequency of that block [7].
E. FILTERING
Filtering is performed finally to eliminate noise and preserve the ridge structures.
F. MINUTUAE EXTRACTION
Among all the fingerprint features, the minutiae feature representation reduces the complex fingerprint recognition
problem to a point pattern matching problem. Minutia points are detected by locating the end points and bifurcation
points on the thinned ridge skeleton based on the number of neighbouring pixels.Minutuae extraction consist of two
technique i.e. binaries finger print image and gray scale finger print image.
G. MINUTUAE MATCHING
At the matching stage, approach is to elastically match minutia. Given two set of minutia of two fingerprint images,
the minutiae matching algorithm determines whether the two minutia sets are from the same finger or not.
III. LITERATURE SURVEY
Benazir.K.K .al [1] presents a fast fingerprint enhancement methodology and new implementation of techniques for
fingerprint enhancement. New consequences show that incorporating the enhancement algorithm improves the
verification accuracy.
Carsten Gottschlich [2] For the purpose of enhancing curved structures in noisy images, he establishes curved Gabor
filters which locally adapt their shape to the direction of flow. These curved Gabor filters allow the choice of filter
parameters which increase the smoothing power without creating artefacts’ in the enhanced image. Curved Gabor filters
are useful to the curved ridge and valley structure of low-quality fingerprint images. First, he combine two orientation
end estimation methods in order to obtain a more robust estimation for very noisy images, curved regions are constructed
by following the respective local orientation and they are used for estimating the local ridge frequency. Lastly, curved
Gabor filters are denied based on curved regions and they are applied for the enhancement of low-quality fingerprint
images. Experimental outcome on the FVC2004 databases show improvements of this approach in comparison to state-
of-the-art enhancement methods.
Vipan KAKKAR.al. [3] Proposed an enhancement method based on Gabor filtering in wavelet domain. Gabor filter is
chosen because it has both frequency-selective and orientation-selective properties and has optimal resolution in both
spatial and frequency area. Filtering is done on the images result from wavelet corrosion and finally, the image is
reconstructed to get the improved image. Experiments are conducted on 500dpi resolution fingerprint images
commercially existing from FVC2002 fingerprint database.
R.Dharmendra Kumar .al.[4] discuss about the enhancement of the finger print image for fingerprint recognition.
This target can be mainly decayed into image pre-processing, feature extraction and feature contest. For each sub-task,
some traditional and up-to-date methods in literatures are analysed. Based on the analysis, an included solution for
fingerprint recognition is developed for demonstration. MATLAB is used in this project. Some optimization at coding
level and algorithm level are proposed to improve the performance of this fingerprint recognition system. These
performance enhancements are shown by experiments conducted upon a variety of fingerprint images. Also, the
experiments exhibit the key issues of fingerprint recognition that are consistent with what the available literatures say.
Dr. S. Pannirselvam .al. [5] he used the high boost filter and Gaussian filter for efficient finger print image quality. In
the planned method the original is filtered using High Pass filter and the Gaussian filter for noise deduction. Finally,
High Boost filter is applied for better enhancement and the performance of the image quality is measured using Mean
Squared Error (MSE) and Peak Signal Noise Ratio (PSNR). It is proved that our methodology provides better result in
improving the image quality and better enhancement.
Sandhya Tarar .al.[6] have planned an algorithm of fingerprint image enhancement by using Iterative Fast Fourier
Transform (IFFT). Iterative image reconstruction algorithms play an important role in fingerprint identification systems
in order to achieve higher degree of efficiency. With the fast raise of the sizes of the fingerprint data, design of the
rebuilding algorithms is of great importance in order to improve the performance. Fourier-based frequency orientation
method have the potential to considerably reduce the computation time in iterative modernization. The Author also has
designed an approach for removing the false minutia generated during the fingerprint processing and a method to reduce
the false minutia to increase the efficacy of identification system. The Author include fingerprint Verification
Competition 2006 (FVC 2006) as a database for implementation of proposed algorithm to verify the degree of efficiency
Gupta et al., International Journal of Advanced Research in Computer Science and Software Engineering 4(6),
June - 2014, pp. 194-200
© 2014, IJARCSSE All Rights Reserved Page | 197
of proposed algorithm. Experimental result shows that the planned enhancement algorithm is better than presented Fast
Fourier Transform algorithm.
Pankaj Deshmukh.al.[7] propose a new method in fingerprint enhancement with application of wavelet transform
which is more efficient than existing methods. At present the methods that are in apply are the ones involving the use of
Gabor filtering and Fourier filtering. But the exactness of these techniques is far from satisfactory. A new technique is
being proposed that incorporate wavelet transform and Gabor filtering. The performance of this technique is discussed in
the paper.
IV. PROPOSED WORK
Fingerprint has remained a very vital index for human recognition. In the field of security, series of Automatic
Fingerprint Identification Systems (AFIS) have been developed. One of the indices for evaluating the contributions of
these systems to the enforcement of security is the degree with which they appropriately verify or identify input
fingerprints. This degree is generally determined by the quality of the fingerprint images and the efficiency of the
algorithm. In this paper, some of the sub-models of an existing mathematical algorithm for the fingerprint image
enhancement were modified to obtain new and improved versions. The new versions consist of different mathematical
models for fingerprint image segmentation, normalization, ridge orientation estimation, ridge frequency estimation,
Gabor filtering and binarization. The implementation was carried out in an environment characterized by Window Vista
Home Basic operating system as platform and Matrix Laboratory (Mat Lab) as frontend engine. Synthetic images as well
as real fingerprints obtained from the FVC2004 fingerprint database DB3 set A were used to test the adequacy of the
modified sub-models and the resulting algorithm. The results show that the modified sub-models perform well with
significant improvement over the original versions. The results also show the necessity of each level of the enhancement.
A. Tool used MATLAB
is a high-level language and interactive environment for numerical computation, visualization, and
programming. Using MATLAB, you can analyze data, develop algorithms, and create models and applications. The
language, tools, and built-in math functions enable you to explore multiple approaches and reach a solution faster than
with spreadsheets or traditional programming languages, such as C/C++ or Java. You can use MATLAB for a range of
applications, including signal processing and communications, image and video processing, control systems, test and
measurement, computational finance, and computational biology. More than a million engineers and scientists in industry
and academia use MATLAB, the language of technical computing.
V. RESULT
1.TYPE COMMAND START_GUI_SINGLE_MODE IN MATLAB 6.0.
Fig 5: The User Interface of the Fingerprint Recognition System.
2. Click Load Button
Fig 6: Load a gray level fingerprint image from a drive specified by Users.
Gupta et al., International Journal of Advanced Research in Computer Science and Software Engineering 4(6),
June - 2014, pp. 194-200
© 2014, IJARCSSE All Rights Reserved Page | 198
3. Click Clahe Button
Fig 7: After Histogram Equalization.
4. Click fft Button
Fig 8: Captured window after click ‘FFT’ button.
5. Click Direction Button
Fig 9: Screen capture after binarization (left) and block direction estimation (right).
6.Click ROI Area Button.
Fig 10 : ROI extraction.
Gupta et al., International Journal of Advanced Research in Computer Science and Software Engineering 4(6),
June - 2014, pp. 194-200
© 2014, IJARCSSE All Rights Reserved Page | 199
7. Click Gabor Filer Button
Fig 11: The Fingerprint image after filtering,
8. Click Extract Button
Fig 12: This show extracts the ridges and valleys in right-hand side.
9. Click Real Minutia Button
Fig 13: Minutia Marking (right) and False Minutia Removal (Left).
10. Click Save Button
Fig 14: Save minutia to a text file.
Gupta et al., International Journal of Advanced Research in Computer Science and Software Engineering 4(6),
June - 2014, pp. 194-200
© 2014, IJARCSSE All Rights Reserved Page | 200
11. Click Match Button
Fig 15: This shows the matching percentage is 100%.
VI. CONCLUSION
The evolution of proposed technique is done in terms of matching score of existing and proposed technique. My project
has combined many methods to build a minutia extractor and a minutia matcher. Also a program coding with MATLAB
going through all the stages of the fingerprint recognition is built. It is helpful to understand the procedures of fingerprint
recognition. And demonstrate the key issues of fingerprint recognition.These techniques can then be used to facilitate the
further study of the statistics of fingerprints.
REFERENCES
[1] BENAZIR.K.K AND R.VIJAYAKUMAR, FAST ENHANCEMENT ALGORITHM WITH IMPROVED CLARITY OF RIDGE
AND VALLEY STRUCTURES FOR FINGERPRINT IMAGES, INDIACOM-2011 ISSN 0973-7529 ISBN 978-93-
80544-00-7.
[2] GOTTSCHLICH, CURVED GABOR FILTERS FOR FINGERPRINT IMAGE ENHANCEMENT, ARXIV:1104.4298V1 [CS.CV]
21 APR 2011.
[3] VIPAN KAKKAR, ABHISHEK SHARMA, T.K. MANGALAM, PALLAVI KAR, FINGERPRINT IMAGE
ENHANCEMENT USING WAVELET TRANSFORM AND GABOR FILTERING, MANUSCRIPT RECEIVED
SEPTEMBER 05, 2011; REVISED NOVEMBER 28, 2011.
[4] R.Dharmendra Kumar, FINGER PRINT IMAGE ENHANCEMENT USING FFT FOR MINUTIA
MATCHING WITH BINARIZATION, International Journal of Engineering Research & Technology
(IJERT)Vol. 1 Issue 8, October – 2012.
[5] Dr.S.Pannirselvam,P.Raajan, An Efficient Finger Print Enhancement Filtering Technique with High Boost
Gaussian Filter (HBG), Volume 2, Issue 11, November 2012 ISSN: 2277 1.
[6] Hongchang Ke,Hui Wang and Degang Kong, An improved Gabor filtering for fingerprint image enhancement
technology, 2nd International Conference on Electronic & Mechanical Engineering and Information Technology
(EMEIT-2012).
[7] Pankaj Deshmukh,Siraj Pathan,Riyaz Pathan,Image Enchancement Techniques For Fingerprint Identification,
International Journal of Scientific and Research Publications, Volume 3, Issue 3, March 2013 1,ISSN 2250-
3153.
[8] Sandhya Tarar and Ela Kumar, Fingerprint Image Enhancement: Iterative Fast Fourier Transform Algorithm
and Performance Evaluation, International Journal of Hybrid Information Technology,Vol. 6, No. 4, July, 2013.