Fingerprint Reconstruction Method Using Partial Differential Equation and Exemplar-Based Inpainting Methods

Abstract

Manual latent fingerprint reconstruction to restore missing ridges is a tedious, time consuming, and expensive process. Latent fingerprint ridges are typically partially smudged, partially missing, aged, etc. This type of fingerprint cannot be used in the court of law directly to garner a conviction unless it can be matched to a known fingerprint. However, latent prints minimize the search for potential suspects and finding missing people. We propose an automated reconstruction method which minimizes manual restoration. Our nonlinear partial differential equation (PDE) and exemplar inpainting processes can aid the fingerprint expert. Larger missing regions are repaired using our coherent-based exemplar inpainting algorithm. PDE inpainting is used to fill small fissures in ridge structure. Ridge-lines are sharpened with anisotropic diffusion filters. These technologies improve latent fingerprint computer matching by allowing more minutiae. Accuracy assessment for inpainting missing ridges is described.