Post on 24-May-2015
description
[1]
Fingerprint RecognitionProject ID-1044
BySandeep Kumar Panda Roll# ECE200910024Sailendra Sagar Patra Roll# ECE200910023
Under the guidance of
Mrs. T. Mita Kumari
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
B.Tech Project Presentation-2013
[2]
B.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
Outline…….• Objective• What is Fingerprint?• What is Fingerprint Recognition?• Algorithms For Fingerprint Recognition.• Preprocessing Stages.• Minutia Extraction.• Minutia Match.• Result And Discussion• Conclusion
[3]
Objective Of Our Project• The objective is to implement Fingerprint Recognition Algorithm by Using
Minutia Extraction and Minutia Matching.
• The objective is to implement fingerprint recognition algorithm. The Region of Interest (ROI) for each fingerprint image is extracted after enhancing its quality.
• That is used to extract the minutia, followed by minutiae extraction.
• Application :• Data Security
• Crime Investigation
• Security Lock
B.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
[4]
What Is Fingerprint?• Skin on human fingertips contains
ridges and valleys which together forms distinctive patterns. These patterns are called FINGERPRINTS.
• However, shown by intensive research on fingerprint recognition, fingerprints are not distinguished by their ridges and furrows, but by features called Minutia, which are some abnormal points on the ridges.
B.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
[5]
• Among the variety of minutia types reported in literatures, two are mostly significant and in heavy usage:
1.Ridge ending- the abrupt end of a ridge
2.Ridge bifurcation- a single ridge that divides into two ridges
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
B.Tech Project Presentation-2013
[6]
What Is Fingerprint Recognition?• Fingerprint recognition is the process
of comparing questioned and known fingerprint against another fingerprint to determine if the impressions are from the same finger or palm.
• It includes two sub-domains: one is fingerprint verification and the other
is fingerprint identification.
B.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
[7]
Algorithms For Fingerprint Recognition
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
B.Tech Project Presentation-2013
Load Image
Histogram Equalization
Enhancement Using FFT
Binarization
Ridge Ending
ROI
Thinning
Minutia Marking
Align And Match Template
Save Template
Image Acquisition
Preprocessing Stages
Minutia Extraction
Minutia Match
[8]
Pre Processing Stages….• Histogram Equalization:1. Histogram equalization is a technique of improving the global contrast of an image
by adjusting the intensity distribution on a histogram.
B.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
Original Histogram Histogram After Equalization
Histogram Equalization Image
[9]
Pre Processing Stages….• Enhancement by Fourier transform:
The image enhancement by FFT is done by the following formula:
Where,
for x=0,1,2,…….,31 and y=0,1,2,…….,31.
B.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
kvuFvuFFyxg ,,, 1
1
0
1
0
2exp,,M
x
N
y N
vy
M
uxjyxfvuF
Enhanced FFT Image
[10]
Pre Processing Stages….• Binarization:• Fingerprint Image Binarization is to transform the 8-bit Gray fingerprint
image to a 1-bit image with 0-value for ridges and 1-value for furrows.• After the operation, ridges in the fingerprint are highlighted with black
colour while furrows are white. A locally adaptive binarization method is performed to binarize the fingerprint image.
• Such a named method comes from the mechanism of transforming a pixel value to 1 if the value is larger than the mean intensity value of the current block (16x16) to which the pixel belongs
B.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
Binarized Image
[11]
Pre Processing Stages….B.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
• Block Direction Estimation• The direction for each block of the fingerprint image with WxW in size(W is 16
pixels by default)is estimated. • The direction for each block of the fingerprint image with WxW in size(W is 16
pixels by default)is estimated.• The gradient values along x-direction (gx) and y-direction (gy) for each pixel of
the block is calculated.• For each block, following formula is used to get the Least Square
approximation of the block direction.
22
2tan
yx
yx
gg
gg
Block Direction Image
[12]
Preprocessing Stages……• ROI(Region Of Interest):• Two Morphological operations called ‘OPEN’ and ‘CLOSE’ are adopted.• The ‘OPEN’ operation can expand images and remove peaks introduced by
background noise.• The ‘CLOSE’ operation can shrink images and eliminate small cavities.
B.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
ROI Image
[13]
Minutia Extraction……..• Ridge Thinning:• Ridge Thinning is to eliminate the redundant pixels of ridges
till the ridges are just one pixel wide.
• An iterative, parallel thinning algorithm is used for ridge thinning.
B.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
Thinned Image
[14]
Minutia Extraction……..• Minutia Marking:• After the fingerprint ridge thinning, marking minutia points is relatively easy.
The concept of Crossing Number (CN) is widely used for extracting the Minutia.
B.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
0 1 0
0 1 0
1 0 1
0 0 0
0 1 0
0 0 1
Bifurcation Termination
Marked Image
[15]
Minutia Matching……..• Minutia match algorithm determines whether the two minutiae sets are
from same finger or not.• It include two stages:-
– Alignment Stage– Match Stage
• Alignment stage:- Given two fingerprint images to be matched, any one minutia from each image is chosen, and the similarity of the two ridges associated with the two referenced minutia points is calculated
• Match stage: After obtaining two set of transformed minutia points, the elastic match algorithm is used to count the matched minutia pairs by assuming two minutia having nearly the same position and direction are identical.
B.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
Matched Image
[16]
RESULT AND DISCUSSION• Histogram Equalization Image:
B.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
Original Image Image After Histogram Equalization
Algorithm
[17]
RESULT AND DISCUSSION• Enhancement by Fourier transform:
B.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
Image After Histogram Equalization
Algorithm
Image After FFT Enhancement
[18]
RESULT AND DISCUSSION• Binarization:
B.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
Algorithm
Image After FFT Enhancement Binarized Image
[19]
RESULT AND EXPERIMENT• Block Direction Estimation:• :
B.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
Algorithm
Binarized Image Block Direction Estimation
[20]
RESULT AND EXPERIMENTB.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
Algorithm
Binarized Image Open Operation Close Operation ROI+Bound
•ROI(Region Of Interest):
[21]
RESULT AND EXPERIMENT• Ridge Thinning:
B.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
Algorithm
ROI Image Thinned Image
[22]
RESULT AND EXPERIMENT• Minutia Marking:
B.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
Algorithm
Thinned Image Minutia Marked Image
[23]
RESULT AND DISCUSSION• Minutia Matching:• Here we had taken two different sets of fingerprints. 1.Two different angles of a same fingerprint 2. Fingerprints of two different finger.• Using Match Score we distinguish two fingerprints are same or not.
B.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
[24]
RESULT AND DISCUSSIONB.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
•The match score value between the two images is 0.67.• This value is greater or same as threshold value.•We conclude that these two fingerprints are of same person.
[25]
RESULT AND DISCUSSIONB.Tech Project Presentation-2013
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
•The match score value between the two images is 0.37.• This value less than threshold value.•We conclude that these two fingerprints are of two different persons.
[26]
Conclusion
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
B.Tech Project Presentation-2013
• The above implementation was an effort to understand how Fingerprint Recognition is used as a form of biometric to recognize identities of human beings.
• It includes all the stages from enhancement to minutiae extraction of fingerprints.
• There are various standard techniques are used in the intermediate stages of processing.
• At last minutiae extraction and comparison happens.
[27]
Reference
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023
B.Tech Project Presentation-2013
• Fingerprint database - FVC2002 (Fingerprint Verification Competition 2002)
• Rafael C .Gonzalez, Richard E Woods “Digital Image Processing”2nd edition, 2002.
• K. Jain, F. Patrick, A. Arun , “Handbook of Biometrics”, Springer Science Business Media, LLC, 1st edition, pp. 1-42, 2008.
• D. Maio, and D. Maltoni, “Direct gray-scale minutia detection in fingerprints”, IEEE Transactions Pattern Analysis and Machine Intelligence, vol. 19(1), pp. 27-40, 1997.
• D. Maltoni, D. Maio, and A. Jain, S. Prabhakar, “4.3: Minutiae-based Methods’(extract) from Handbook of Fingerprint Recognition”, Springer, New York, pp. 141-144, 2003.
• E. Hastings, “A Survey of Thinning Methodologies”, Pattern analysis and Machine Intelligence, IEEE Transactions, vol. 4, Issue 9, pp. 869-885, 1992.
[28]
THANK YOU
Sandeep Kumar Panda Roll # ECE200910024Sailendra Sagar Patra Roll # ECE200910023