Abstract

Post-mortem fingerprints are a valuable biometric used to aid in the identification of a deceased individual. However, fingerprints from the deceased undergo decomposition leading to indefinite structure when compared to ante-mortem fingerprints. Moreover, the performance of the existing two-dimensional (2D) fingerprint recognition systems is still below the expected potential. These problems arise because fingerprints are generally captured by manipulating a finger against a plane. In post-mortem fingerprint recovery, the decedent's finger must go through several reconditioning processes to prevent the rapid onslaught of decomposition. To address these deficiencies associated with the 2D systems, three-dimensional (3D) scanning systems have been employed to capture fingerprints. The 3D technology is still in its transient phase and is limited primarily by 1) the lack of existing 3D databases; 2) the deficiency of 3D-to-2D fingerprint image mapping algorithms, 3) the incapacity to model and recreate the 2D fingerprint capturing procedure to improve 3D-2D fingerprint verification; and 4) the inability to apply traditional fingerprint unrolling techniques on post-mortem 3D fingerprints. This paper presents a novel method to perform post-mortem 3D fingerprint unrolling and pressure simulation to produce fingerprint images that are compatible with 2D fingerprint recognition systems. The thrust of this paper strives to: 1) develop a correspondence between 3D touchless and contact-based 2D fingerprint images; 2) model fingerprints with deformities to provide a viable fingerprint image for matching and; 3) develop a mosaic pressure simulation (MPS) algorithm to recreate the effects of 2D fingerprint capturing procedure.

Highlights

  • Biometrics refers to any human physiological or behavioral trait, which can be used for identification and verification [1], [2]

  • The Mosaic Pressure Simulation (MPS) output images are subjected to a wide variety of distortions and changes during capture, pre-processing, unrolling, pressure simulation, and image mosaicking

  • MPS solves the problem of interoperability of authenticating 3D and 2D fingerprint images effectively by producing realistic images

Read more

Summary

INTRODUCTION

Biometrics refers to any human physiological or behavioral trait, which can be used for identification and verification [1], [2]. The process involves (i) capturing a 3D image of the deceased’s finger after reconditioning and recovering, (ii) modeling the object onto a flat surface whilst maintaining the ridge mesh integrity and considering the severe deformations that may exist on the post mortem finger, (iii) resampling the unrolled image to improve structural integrity, (iv) rolling back the flat 3D image to the shape of a finger, (v) dividing the 3D image into ‘n’ cross-sections and simulating pressure on each crosssection, and (vi) mosaicking each cross-section to provide an unrolled pressure simulated finger image This process is repeated iteratively with different levels of pressure to improve the probability of finding a correct match.

RELATED WORK
ANOMALY REMOVAL AND TEXTURE EXTRACTION
PRESSURE SIMULATION ON CROSS-SECTIONS OF FINGER
Findings
CONCLUSION
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call