Btech Project Presentation
Fingerprint Analysis for Identification & Classification Guides: Dr. Suman K. Mitra Dr. Asim Banerjee Dr. Anil K. Roy
By Shalabh Jain 200201176
DhiruBhai Ambani Institute of Information & Communication Technology
Fingerprint Identification
What is Fingerprint Identification Application of Fingerprint Identification Approach for the above purpose
Minutiae
Ridge Bifurcation
A Sample Fingerprint
Ridge Ending
0
1
0
0
0
0
0
1
0
0
1
0
1
0
1
1
0
0
Features extracted from Minutiae Minutia Type
Ridge ending Ridge Bifurcation
Minutia Orientation
Connecting Pixels Convention Adopted
Minutia Level
Horizontal Level Vertical Level
4
3
2
5
x
1
6
7
8
Sample Graph Representation
Id x-cood
y-cood
Type
Connecting pixel1
Connecting pixel2
Horizontal Level
Vertical Level
1
6
132
0
1
7
1
12
2
16
286
1
1
0
1
7
3
28
238
0
2
8
1
11
4
45
218
1
3
0
2
10
Matrix Formation
B1
B2
_
_
Bn
A1
1
1
1
1
1
A2
1
1
1
1
1
|
1
1
1
1
1
|
1
1
1
1
1
Am
1
1
1
1
1
Elimination
Stage 1: - Elimination by minutia type Stage 2: - Elimination by level comparison Stage 3: - Elimination by orientation comparison
Output is a refined matrix with very few potential matches for each minutiae
Refined Matrix
B1
B2
_
_
Bn
A1
0
1
0
1
0
A2
1
0
0
1
0
|
0
1
1
0
0
|
0
0
1
0
1
Am
0
0
0
0
1
Edge Information
Distance between two nodes
Calculated using the x-y co-ordinates stored earlier
Ridge Density between two nodes
Refined Matrix
B1
B2
_
Bn-1
Bn
A1
0
1
0
1
0
A2
1
0
0
1
0
|
0
1
1
0
0
|
0
0
1
0
1
Am
0
0
0
0
1
Final Output Matrix
B1
B2
_
_
Bn
Sum
A1
0
1
0
0
0
1
A2
1
1
0
0
0
2
|
0
0
1
0
0
1
|
0
0
0
0
0
0
Am
0
0
0
1
0
1
* A fingerprint can be rejected on basis of this matrix, during elimination stages
Database for Testing
Complete print
Partial print I
Partial print II
Experimental Results -I Intra Class Type (No. of Images)
Total Cases
Correct Accepts
Correct Rejects
False Accept
False Reject
Left Loop (42)
861
28
822
11
5
Right Loop (31)
465
19
440
0
6
Whorl (34)
561
22
526
7
6
Arch (28)
378
21
349
5
3
Experimental Results -II Inter Class Total Fingerprints
125
Total Cases
7750
Correct Accepts
82
Correct Rejects
7646
False Acceptance
12
False Rejects
10
Conclusions & Future work
Less compute intensive due to elimination stages Not dependent on singularities, so robust against partial prints Should be robust against distortions Time and Space efficient Fingerprint classification can reduce further time
Selected References [1]
D. K. Isenor, S. G. Zaky, “Fingerprint Identification using graph matching”, Pattern Recognition, volume 19, No. 2, pp. 113 122. (1986).
[2]
Xudong Jiang; Wei-Yun Yau; “Fingerprint minutiae matching based on the local and global structures”, Proceedings. 15th International Conference on Pattern Recognition, volume 2, pp. 1038 - 1041, (2000)
[3]
D. Maltoni, D. Maio, A.K. Jain and S. Prabhakar, “Handbook of Fingerprint Recognition”, Springer (New York),(2003).
[4]
N. Yager, A. Amin, “Fingerprint Classification: a review”, Pattern Analysis Application, pp:7:77-93 (2004)
[5]
U. Pal, S. Sinha and B. B. Chaudhuri, "Multi-script line identification from Indian documents", Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR), pp. 880 – 884, (2003)
[6]
U. Pal; S. Datta; “Segmentation of Bangla Unconstrained Handwritten Text” Proceedings. Seventh International Conference on Document Analysis and Recognition. pp :1128 – 1132, (2003)
Thank You !
