Novel fingerprint aging features using binary pixel sub-tendencies: A comparison of contactless CLSM and CWL sensors

Abstract

Age determination of latent fingerprints from crime scenes is an open challenge to forensic experts since several decades. In recent publications it was shown that a feature called binary pixel in combination with a contactless and non-invasive Chromatic White Light (CWL) image sensor is able to distinguish between fingerprints younger as or older than five hours with an accuracy of about 70-80%. Such approach can be seen as a very promising first step, but needs to be improved (e.g. by a fusion with additional aging features) to reach error rates that would be acceptable in legal proceedings. In the scope of this paper, two novel aging features are introduced and evaluated as opposing sub-tendencies of the classical binary pixel feature. Furthermore, Confocal Laser Scanning Microscopy (CLSM) is firstly applied to fingerprint aging evaluations. In our experiments, 200 fingerprint time series (captured every hour for 24 hours) for each the novel CLSM as well as the classical CWL device (9600 fingerprint images in total) are evaluated and compared using the classical binary pixel feature as well as both novel sub-tendency features. We show that one of such new sub-tendencies performs very well for the CLSM device (90% of curves show a strong logarithmic aging behavior), while for the CWL sensor the classical binary pixel feature performs best (87% of curves showing a strong logarithmic aging behavior). The increased performance of such new feature can be seen as very suitable for complementing the classical CWL binary pixel aging feature in a future age estimation approach.