Learning Fingerprint Reconstruction: From Minutiae to Image

Abstract

Abstract-The set of minutia points is considered to be the most distinctive feature for fingerprint representation and is widely used in fingerprint matching. It was believed that the minutiae set does not contain sufficient information to reconstruct the original fingerprint image from which minutiae were extracted. However, recent studies have shown that it is indeed possible to reconstruct fingerprint images from their minutiae representations. Reconstruction techniques demonstrate the need for securing fingerprint templates, improve the template interoperability and improve fingerprint synthesis. But, there is still a large gap between the matching performance obtained from original fingerprint images and their corresponding reconstructed fingerprint images. In this paper, the prior knowledge about fingerprint ridge structures is encoded in terms of orientation patch and continuous phase patch dictionaries to improve the fingerprint reconstruction. The orientation patch dictionary is used to reconstruct the orientation field from minutiae, while the continuous phase patch dictionary is used to reconstruct the ridge pattern. Experimental results on three public domain databases (FVC2002 DB1 A, FVC2002 DB2 A and NIST SD4) demonstrate that the proposed reconstruction algorithm outperforms the stateof-the-art reconstruction algorithms in terms of both i) spurious and missing minutiae and ii) matching performance with respect to type-I attack (matching the reconstructed fingerprint against the same impression from which minutiae set was extracted) and type-II attack (matching the reconstructed fingerprint against a different impression of the same finger).Index Terms-fingerprint reconstruction, orientation patch dictionary, continuous phase patch dictionary, minutiae set, AM-FM model.

Sensors of Smart Devices in the Internet of Everything (IoE) Era: Big Opportunities and Massive Doubts

“…Other studies went even further by constructing a fingerprint image from minutiae. The results showed that there is a very high resemblance between the original and the reconstructed fingerprint [38]. Ben-Asher et al suggested a two-step authentication method where the fingerprint, combined with the touchscreen, is used to verify or identify the user [39].…”

Fingerprint: A Unique and Reliable Method for Identification

“…It, therefore, leaves the scene much cleaner than when using black powder. 63,64 Patent fingerprints can be made by blood, grease, ink or dirt. This type of fingerprint is easily visible to the human eye.…”

Bit-string representation of a fingerprint image by normalized local structures

“…For instance, as smartphones and IoT-enabled devices are always connected to network, the system is easily exposed to diverse attacks [5], which cause permanent loss of private biometric information. According to [6], [7], [8], [9], original fingerprint images could be reconstructed from their ge-ometrical minutia data, so if a hostile entity compromises the fingerprint template, the biometric identity cannot be used permanently [10]. For secure protection of fingerprint templates, a cancelable fingerprint template [11], [12], [13], [14] and bio-encryption [15], [16] have been proposed [17], [18], however, some of these solutions can only be adopted when the fingerprint is represented by an ordered and fixed-length bit-vector [13], [14], [19].…”