spurious minutiae resulting from these crack, is based on theobservation that these minutiae are anti-aligned and the regionbetween them is brighter than the average brightness of theforeground region. Hong et. al.[8] improved thecomputationally expensive enhancement method [6], whichmakes it unsuitable for an online verification system. Theauthors have presented a fast enhancement algorithm toenhance adaptively, the ridge and furrow structures using boththe local ridge orientation and local frequency information.Yang et. al.[9] modified the method proposed by Hong et. al.[8] by discarding the inaccurate prior assumption of sinusoidalplane wave, and making the parameter selection processindependent of fingerprint image. Rajkumar andHemachandran [15] used both FFT and Gaussian filter forfingerprint enhancement in preprocessing stage. FFT have 32 X32 pixel block size and Gaussian filter gives little blur by giving
σ =0.5 which used in
removing the hairy structure when it isthinning.
2
P
ROPOSED
A
LGORITHM
An automatic fingerprint identification system consists ofvarious processing stages. The overall process of the proposedalgorithm can be divided into four main operations:2.1
Image enhancement2.2
Binarization and thinning2.3
Feature extraction and its purification2.4
Demarcation of boundary feature
2.1. Fingerprint Enhancement
In this study two methods are used for Image enhancementprocess: (i) Normalization and (ii) Fast Fourier Transformation.
Fig 2. Proposed algorithm for Fingerprint Identification System
(i) Normalization
Normalization is done so that the gray level values lies withina given set of values. The fingerprint image is normalized tohave a predefined mean and variance. The normalization isrequired as the fingerprint image usually has distorted levelsof gray values among the ridges and furrows. This is a pixel-wise operation although it does not change the ridge andfurrows structure. Let I(i,j) denotes the gray-level value at pixel(i,j), M and VAR denote the estimated mean and variance of I,respectively, and G(i,j) denote the normalized gray-level valueat pixel (i,j).The norma
lized image is defined as follows [ 9]:
,
=
+
VAR
O
I
i,j
−
M
2
VAR
,
,
>
.
−
,
−
2
,
,
≤
(1)
where MO and VARO are the desired mean and variancevalues, respectively.Normalization is achieved by histogram equalization. Itincreases the local contrast in an image. Thus the intensities canbe distributed on the histogram. This allows for areas of lowerlocal contrast to gain a higher contrast without affecting theglobal contrast. Histogram equalization accomplishes this byeffectively spreading out the intensity values.
(ii) Fast Fourier Transformation
The primary enhancement is done through Fouriertransformation. Initially the fingerprint image is divided intosmall processing blocks (32 X 32 pixels) and the Fouriertransformation is performed according to the followingequation:
,
=
.
−
1
=0
.
−
1
=0
,
∗
exp
−
2
∗
+
(2)
for u = 0,1,2,….,31 and v = 0,1,2,….,31.
In order to enhance a specific block by its dominantfrequencies, the FFT of the block was multiplied by itsmagnitude a set of times. Where the magnitude of the originalFFT = |F(u,v)|.The enhanced block is obtained according to
g
x,y
=F
−
1
F
u,v
∗
|F
u,v
|
K
(3)where F-1 (F(u,v)) is done by:
,
=1
−
1
=0
,
−
1
=0
∗
exp
2
∗
+
(4)
for
x
= 0, 1, 2, ..., 31 and y = 0, 1, 2, ..., 31.
The k in (3) is an experimentally determined constant, as k= 0.45. While having a higher "k" value improves theappearance of the ridges, by filling up small holes in ridges andhaving a too high "k" value can result in false joining of ridges.Thus a termination might become a bifurcation.
2.2. Binarization and Thinning
This process is used to convert the gray scale image totwo bit image (black and white) and after the ridge pixel iseliminate to one pixel wide. The details of this process aredescribed below:
(i) Binarization
The Fingerprint image binarization is to transform the8-bit gray fingerprint image to a 1-bit image with 0 value forridges and 1 value for furrows. After the operation, ridges in
FingerprintimageFingerprintfeature
Binarizationand ThinningFeatureextraction &purificationTaking ROI
Imageenhancement
JOURNAL OF COMPUTING, VOLUME 4, ISSUE 5, MAY 2012, ISSN 2151-9617https://sites.google.com/site/journalofcomputingWWW.JOURNALOFCOMPUTING.ORG79