Sunday, February 28, 2021

Using the NCIC Bayesian Network to improve your AFIS searches

Using over 21 million sets of Tenprint cards, the NCIC Bayesian Network allows an examiner to appreciate the relative rarity of general patterns on fingerprints and can assist with the selection of the best fingers to search for on AFIS.

Must read

Michael Whyte
Crime Scene Officer and Fingerprint Expert with over 12 years experience in Crime Scene Investigation and Latent Print Analysis. The opinions or assertions contained on this site are the private views of the author and are not to be construed as those of any professional organisation or policing body.
- Forensic Podcast -

This National Crime Information Centre (NCIC) Bayesian network is based on the statistical data of general patterns of fingerprints on the hands of 17,951,192 males and 4,313,521 females respectively. These datasets have been compiled by the FBI and National Institute of Justice (NIST).

The general patterns and associated measures (ridge counts for loops and ridge tracing for whorls) are based on the Galton-Henry classification used at the time by the FBI.This network allows computing probabilities associated with various situations of forensic interest.

For example, an examiner is in the process of searching a particular latent on their AFIS system. An examiner may want to know the statistical distribution of the general patterns for a given finger number (1 to 5 for the right hand and 6 to 10 for the left hand, from thumb to little finger) and sex. Or alternatively if he/she observes a fingerprint with given attributes (in terms of general pattern and associated measures), he may want to predict the finger number or the sex.

This can be very beneficial for performing narrow searches on only a 2-3 fingers for a difficult latent with limited detail. For instance, you may have a plain whorl with an outside ridge tracing. By selecting these 2 options the Network returns results of the right thumb, right ring, and left index fingers as having the highest probability. The examiner searches these 3 fingers again the unknown latent for a possible candidate to compare. If a candidate isn’t found on this narrow search, an examiner can then perform a wider search.

Using the Bayesian Network for computing probabilities associated with various situations of forensic interest.

Ultimately, this Bayesian Network allows the examiner to appreciate the relative rarity of general patterns on fingerprints and can help making a selection of the best fingers to search for based on the pattern left by unknown source.

You can view and experiment with the Network by clicking on this link here.

- Advertisement -

More articles

- Advertisement -

Latest article