Creation of a Public Corpus of Contact-Less Acquired Latent Fingerprints without Privacy Implications

Abstract

Abstract. Data sets of biometric or forensic samples are an important basis for evaluations and research. Especially biometric data is considered as personal data, which is protected by privacy regulations. Since the data cannot be altered or revoked, at least in some countries, this poses a challenge because rights must be granted to the data's subject. In particular in Germany and probably in the entire European Union after its reformation of the data protection legislation it is challenging to use such data. Furthermore, with respect to latent fingerprints only very few public data sets exist nowadays. We propose the creation of a public data set without privacy implications consisting of latent fingerprints from artificial fingerprint patterns. On the foundation of a first set of 50 fingerprints on a compact disk surface we report challenges that need to be solved in order to create realistic samples.

On the Use of Benford’s Law to Detect JPEG Biometric Data Tampering

“…DB1 and DB4 were used for our experiments. The third data set used was from contactless acquired computer generated and printed latent fingerprints [11] for our artificially printed contact-less acquired latent fingerprint images which are stored as gray-scale images with 32 bit colour depth.…”

“…For instance, fingerprints captured using optical sensors maybe used for collecting a country's biometric fingerprint database, where as synthetic generated fingerprints are used for testing fingerprint recognition algorithms which require large databases and collecting real fingerprints for such large databases is very expensive, boring and problematic [12]. The contact-less acquired latent fingerprints were generated for evaluation and research purposes with the aim of avoiding privacy implications [11]. The fingerprints generated by Hildebrandt et al [11] are different from synthetically generated fingerprints in that, the synthetically generated datasets by SFinGe [12] are printed using a Canon Pixma iP4950 ink-jet printer with artificial sweat [11].…”

“…The contact-less acquired latent fingerprints were generated for evaluation and research purposes with the aim of avoiding privacy implications [11]. The fingerprints generated by Hildebrandt et al [11] are different from synthetically generated fingerprints in that, the synthetically generated datasets by SFinGe [12] are printed using a Canon Pixma iP4950 ink-jet printer with artificial sweat [11].…”

“…For example, contact-less acquired latent fingerprints used in this study is meant to be used for research purposes in investigating crime scene forensics [11], synthetic fingerprints is meant for research purposes for performance evaluation, training and testing fingerprint-based systems [12] and optically acquired fingerprints maybe used for a country's biometric database.…”

An Investigation of Benford’s Law Divergence and Machine Learning Techniques for Intra-Class Separability of Fingerprint Images

“…Biometric experts have been dependent on fingerprints over the years for verification and identification purposes. There exist different types of fingerprint images which include contact-less acquired fingerprints, optically acquired fingerprints, and synthetically generated fingerprints (Hildebrandt et al, 2013;Maltoni et al, 2009). Since these fingerprints are used for different purposes, they should not be intentionally or unintentionally used for another purpose as this may cause a serious security threat (Iorliam et al, 2016).…”