Forensic Comparison and Matching of Fingerprints: Using Quantitative Image Measures for Estimating Error Rates Through Understanding and Predicting Difficulty

• NCJ Number: 250158
• Author(s): Philip J. Kellman; Jennifer Mnookin; Patrick Garrigan; Gennady Erlikhman; Tandra Ghose; Everett Mettier; David Charlton; Itiel E. Dror
• Date Published: May 2014
• Length: 14 pages
• Grant Number(s): 2009-DN-BX-K225
• Agencies: NIJ-Sponsored
• Publication Type: Research (Applied/Empirical); Report (Study/Research); Report (Grant Sponsored)
• Award: Error Rates for Latent Fingerprinting as a Function ofVisual Complexity and Cognitive Difficulty

Annotation

In measuring expert fingerprint examiner performance and judgments of difficulty and confidence on a new fingerprint database, this project developed a number of quantitative measures of image characteristics and used multiple regression techniques to discover objective predictors of error as well as perceived difficulty and confidence.

Abstract

A number of useful predictors emerged. These included variables related to image quality metrics, such as intensity and contrast information, as well as measures of information quantity, such as the total fingerprint area. Also included were configural features that fingerprint experts have noted, such as the presence and clarity of global features and fingerprint ridges. Within the constraints of the overall low error rates of experts, a regression model incorporating the derived predictors demonstrated reasonable success in predicting objective difficulty for print pairs. This was shown both in goodness of fit measures to the original data set and in a cross-validation test. The results show the plausibility of using objective image metrics to predict expert performance and subjective assessment of difficulty in fingerprint comparisons. 5 tables, 6 figures, and 47 references