Latent Fingerprint Matching using Descriptor Based Hough Tranform- presentation

1. Latent Fingerprint Matching
Using Descriptor-Based
Hough Transform
1
Guided By
Jose Martin M.J
Presented By
Vishakh K.V
Roll no: 61

2. INTRODUCTION
Law enforcement agencies are used since the early 20th century
Automated Fingerprint Identification System (AFIS)
A new AFIS is introduced for latent fingerprint matching which is not
currently existing
2

3. 3
TYPES OF FINGERPRINTS
Fig. 1. Three types of fingerprint impressions. Rolled and plain fingerprints are also called full
fingerprints. (a) Rolled; (b) plain; (c) latent.

4. 4
LATENT FINGERPRINTS
 Lifted from surfaces of objects that are inadvertently touched or handled
 Usually smudgy and blurred, capture only a small finger area
 Large nonlinear distortion due to pressure variations
Fig. 2. Latent fingerprints of three different quality levels in NIST SD27.
(a) Good; (b) bad; (c) ugly.

5. 5
MINUTIA
Most important aspect in fingerprint analysis
Manually marked in latents
Automatically extracted from rolled fingerprints
Fig.3. Fingerprint minutiae

6. 6
LATENT MATCHING APPROACH
Fig. 4. Overview of the proposed approach

7. 7
LATENT MATCHING APPROACH (Cont….)
A. Feature Extraction
1) Local Minutia Descriptor
 Based on minutiae
 Minutia Cylinder Code (MCC) – minutia based
descriptor
 Records neighbourhood minutia information as
3D function
 Can be concatenated as a vector
Fig.5.(a) Latent and corresponding rolled
print with a mated minutiae pair indicated(b)
Sections of the cylinder corresponding to the
minutia indicated in the latent and in the
rolled print

8. 8
2) Orientation Field Reconstruction
 Minutiae based orientation field reconstruction
algorithm is used
 Estimates local ridge orientation in a block
Fig. 6. Latent fingerprint in NIST SD27 and the reconstructed orientation field
overlaid on the latent.

9. 9
B. Alignment (registration)
 Based on minutia matching
 Estimation of rotational and translational parameters
 Ratha et al. introduced an alignment which uses Generalized Hough
Transform
 Most similar minutia pair is used as base for transformation
parameters
 Our approach uses Descriptor-based Hough Transform (DBHT)

10. 10
Parameter computation
 Let be the minutiae sets,
 To get efficient and accurate alignment,
1. voting using DBHT
2. use of minutia pair that previously votes for a peak

11. 11
ALGORITHM : Descriptor-based Hough Transform

12. 12
ALGORITHM (Cont….)

13. 13
C. Similarity Measure
 For each alignment, a matching score between two fingerprints is computed
 The minutiae matching score between the two fingerprints is given by
Where,
denotes the similarity between the minutia cylinder codes of the ith pair of matched minutiae
maps the spatial distance of the ith pair of matched minutiae into a
similarity score
 Take two values for Ts and mean of two matching score for two threshold are
taken

14. 14
Fig. 7 (a)–(c) shows the latent, the true mate, and the rank-1 nonmate according to large threshold,
respectively. (d)–(g) shows latent minutiae that were matched to rolled print minutiae in the following
cases: (d) true mate using small threshold; (e) true mate using large threshold; (f) nonmate using small
threshold; and (g) nonmate using large threshold. In (d)–(g), the scores corresponding to each case are
included.

15. 15
Given the aligned latent orientation field and the rolled orientation
field , each containing k blocks, namely and , the similarity
between the two orientation fields is given by
where, is 1 if both corresponding blocks are valid, and 0
otherwise.
The overall matching score is given by
where the weight is empirically set as 0.4

16. Fig. 8. (a)–(c) show minutiae and the image of (a) a latent, (b) its true mate, and (c) the highest ranked
nonmate according to minutiae matching. (d) and (f) show latent minutiae and orientation field (in blue)
16
aligned with minutiae and orientation field of the true mate. (e) and (g) show latent minutiae and
orientation field (in blue) aligned with minutiae and orientation field of the nonmate.

17. 17
EXPERIMENTAL RESULTS
Fig. 9. Performance of COTS2, MCC SDK, and Proposed Matcher when the union of manually marked minutiae
(MMM) extracted from latents and automatically extracted minutiae by COTS2 from rolled prints is input to the
matchers. (a) NIST SD27; (b) WVU LFD.

18. 18
CONCLUSIONS AND FUTURE WORK
 Presented a fingerprint matching algorithm using
Descriptor Based-Hough Transform
 Proposed system outperforms the well known
commercial matchers
 Scope of developing an indexing algorithm to speed up
to include a texture-based descriptor to improve the
matching accuracy

19. 19
REFERENCES
 A. A. Paulino, J. Feng, and A. K. Jain, “Latent fingerprint matching
using descriptor-based Hough transform,” in Proc. Int. Joint
Conf. Biometrics,
Oct. 2011, pp. 1–7.
Paulino,Feng,Jain Latent FP Matching Using Descriptor Based
Hough Transform_IJCB11
 Wikipedia

20. 20

21. 21
THANK YOU